# Daily Paper Digest - Generated at: 2026-04-08 17:10:24 (Asia/Shanghai) - Lookback window: last 24 hours ## LLM 1. [Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework](https://arxiv.org/abs/2604.06170v1) - Published: 2026-04-08 01:59 - Authors: Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal - Source: arxiv - Categories: cs.CL - PDF: https://arxiv.org/pdf/2604.06170v1 - Summary: The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools. In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature. The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-criteria scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes such as concepts, methods, experiments, and figures, enabling graph-aware question answering and coverage verification. Both pipelines are implemented within a coder LLM-based multi-agent orchestration framework and produce fully reproducible, synchronized outputs including JSON, CSV, BibTeX, Markdown, and HTML at each agent step. This paper describes the system architecture, agent roles, retrieval and scoring methods, knowledge graph schema, and evaluation interfaces that together form the Paper Circle research workflow. We benchmark Paper Circle on both paper retrieval and paper review generation, reporting hit rate, MRR, and Recall at K. Results show consistent improvements with stronger agent models. We have publicly released the website at https://papercircle.vercel.app/ and the code at https://github.com/MAXNORM8650/papercircle. 2. [Topological Characterization of Churn Flow and Unsupervised Correction to the Wu Flow-Regime Map in Small-Diameter Vertical Pipes](https://arxiv.org/abs/2604.06167v1) - Published: 2026-04-08 01:59 - Authors: Brady Koenig, Sushovan Majhi, Atish Mitra, Abigail Stein, Burt Todd - Source: arxiv - Categories: cs.LG, math.AT - PDF: https://arxiv.org/pdf/2604.06167v1 - Summary: Churn flow-the chaotic, oscillatory regime in vertical two-phase flow-has lacked a quantitative mathematical definition for over $40$ years. We introduce the first topology-based characterization using Euler Characteristic Surfaces (ECS). We formulate unsupervised regime discovery as Multiple Kernel Learning (MKL), blending two complementary ECS-derived kernels-temporal alignment ($L^1$ distance on the $χ(s,t)$ surface) and amplitude statistics (scale-wise mean, standard deviation, max, min)-with gas velocity. Applied to $37$ unlabeled air-water trials from Montana Tech, the self-calibrating framework learns weights $β_{ECS}=0.14$, $β_{amp}=0.50$, $β_{ugs}=0.36$, placing $64\%$ of total weight on topology-derived features ($β_{ECS} + β_{amp}$). The ECS-inferred slug/churn transition lies $+3.81$ m/s above Wu et al.'s (2017) prediction in $2$-in. tubing, quantifying reports that existing models under-predict slug persistence in small-diameter pipes where interfacial tension and wall-to-wall interactions dominate flow. Cross-facility validation on $947$ Texas A&M University images confirms $1.9\times$ higher topological complexity in churn vs. slug ($p < 10^{-5}$). Applied to $45$ TAMU pseudo-trials, the same unsupervised framework achieves $95.6\%$ $4$-class accuracy and $100\%$ churn recall-without any labeled training data-matching or exceeding supervised baselines that require thousands of annotated examples. This work provides the first mathematical definition of churn flow and demonstrates that unsupervised topological descriptors can challenge and correct widely adopted mechanistic models. 3. [The Character Error Vector: Decomposable errors for page-level OCR evaluation](https://arxiv.org/abs/2604.06160v1) - Published: 2026-04-08 01:56 - Authors: Jonathan Bourne, Mwiza Simbeye, Joseph Nockels - Source: arxiv - Categories: cs.CV, cs.LG - PDF: https://arxiv.org/pdf/2604.06160v1 - Summary: The Character Error Rate (CER) is a key metric for evaluating the quality of Optical Character Recognition (OCR). However, this metric assumes that text has been perfectly parsed, which is often not the case. Under page-parsing errors, CER becomes undefined, limiting its use as a metric and making evaluating page-level OCR challenging, particularly when using data that do not share a labelling schema. We introduce the Character Error Vector (CEV), a bag-of-characters evaluator for OCR. The CEV can be decomposed into parsing and OCR, and interaction error components. This decomposability allows practitioners to focus on the part of the Document Understanding pipeline that will have the greatest impact on overall text extraction quality. The CEV can be implemented using a variety of methods, of which we demonstrate SpACER (Spatially Aware Character Error Rate) and a Character distribution method using the Jensen-Shannon Distance. We validate the CEV's performance against other metrics: first, the relationship with CER; then, parse quality; and finally, as a direct measure of page-level OCR quality. The validation process shows that the CEV is a valuable bridge between parsing metrics and local metrics like CER. We analyse a dataset of archival newspapers made of degraded images with complex layouts and find that state-of-the-art end-to-end models are outperformed by more traditional pipeline approaches. Whilst the CEV requires character-level positioning for optimal triage, thresholding on easily available values can predict the main error source with an F1 of 0.91. We provide the CEV as part of a Python library to support Document understanding research. 4. [MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control](https://arxiv.org/abs/2604.06156v1) - Published: 2026-04-08 01:55 - Authors: Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, et al. - Source: arxiv - Categories: cs.CV, cs.AI, cs.CL - PDF: https://arxiv.org/pdf/2604.06156v1 - Summary: MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency. 5. [Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement](https://arxiv.org/abs/2604.06155v1) - Published: 2026-04-08 01:54 - Authors: Qimin Zhong, Hao Liao, Haiming Qin, Mingyang Zhou, Rui Mao, Wei Chen, et al. - Source: arxiv - Categories: cs.LG, cs.AI, cs.CL - PDF: https://arxiv.org/pdf/2604.06155v1 - Summary: Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in learning more structured representations. In this work, we provide a theoretical perspective analyzing the gradient inductive bias of MTP, supported by empirical evidence, showing that MTP promotes the convergence toward internal belief states by inducing representational contractivity via gradient coupling. However, we reveal that standard MTP often suffers from structural hallucinations, where discrete token supervision encourages illegal shortcuts in latent space that violate environmental constraints. To address this, we propose a novel method Latent Semantic Enhancement MTP (LSE-MTP), which anchors predictions to ground-truth hidden state trajectories. Experiments on synthetic graphs and real-world Manhattan Taxi Ride show that LSE-MTP effectively bridges the gap between discrete tokens and continuous state representations, enhancing representation alignment, reducing structural hallucinations, and improving robustness to perturbations. 6. [Who Governs the Machine? A Machine Identity Governance Taxonomy (MIGT) for AI Systems Operating Across Enterprise and Geopolitical Boundaries](https://arxiv.org/abs/2604.06148v1) - Published: 2026-04-08 01:51 - Authors: Andrew Kurtz, Klaudia Krawiecka - Source: arxiv - Categories: cs.CR, cs.AI, cs.MA - PDF: https://arxiv.org/pdf/2604.06148v1 - Summary: The governance of artificial intelligence has a blind spot: the machine identities that AI systems use to act. AI agents, service accounts, API tokens, and automated workflows now outnumber human identities in enterprise environments by ratios exceeding 80 to 1, yet no integrated framework exists to govern them. A single ungoverned automated agent produced $5.4-10 billion in losses in the 2024 CrowdStrike outage; nation-state actors including Silk Typhoon and Salt Typhoon have operationalized ungoverned machine credentials as primary espionage vectors against critical infrastructure. This paper makes four original contributions. First, the AI-Identity Risk Taxonomy (AIRT): a comprehensive enumeration of 37 risk sub-categories across eight domains, each grounded in documented incidents, regulatory recognition, practitioner prevalence data, and threat intelligence. Second, the Machine Identity Governance Taxonomy (MIGT): an integrated six-domain governance framework simultaneously addressing the technical governance gap, the regulatory compliance gap, and the cross-jurisdictional coordination gap that existing frameworks address only in isolation. Third, a foreign state actor threat model for enterprise identity governance, establishing that Silk Typhoon, Salt Typhoon, Volt Typhoon, and North Korean AI-enhanced identity fraud operations have already operationalized AI identity vulnerabilities as active attack vectors. Fourth, a cross-jurisdictional regulatory alignment structure mapping enterprise AI identity governance obligations under EU, US, and Chinese frameworks simultaneously, identifying irreconcilable conflicts and providing a governance mechanism for managing them. A four-phase implementation roadmap translates the MIGT into actionable enterprise programs. 7. [Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization](https://arxiv.org/abs/2604.06138v1) - Published: 2026-04-08 01:45 - Authors: Yanis Labrak, David Grünert, Séverin Baroudi, Jiyun Chun, Pawel Cyrta, Sergio Burdisso, et al. - Source: arxiv - Categories: cs.SD, cs.AI - PDF: https://arxiv.org/pdf/2604.06138v1 - Summary: Long-context audio reasoning is underserved in both training data and evaluation. Existing benchmarks target short-context tasks, and the open-ended generation tasks most relevant to long-context reasoning pose well-known challenges for automatic evaluation. We propose a synthetic data generation pipeline designed to serve both as a training resource and as a controlled evaluation environment, and instantiate it for first-visit doctor-patient conversations with SOAP note generation as the task. The pipeline has three stages, persona-driven dialogue generation, multi-speaker audio synthesis with overlap/pause modeling, room acoustics, and sound events, and LLM-based reference SOAP note production, built entirely on open-weight models. We release 8,800 synthetic conversations with 1.3k hours of corresponding audio and reference notes. Evaluating current open-weight systems, we find that cascaded approaches still substantially outperform end-to-end models. 8. [Shot-Based Quantum Encoding: A Data-Loading Paradigm for Quantum Neural Networks](https://arxiv.org/abs/2604.06135v1) - Published: 2026-04-08 01:44 - Authors: Basil Kyriacou, Viktoria Patapovich, Maniraman Periyasamy, Alexey Melnikov - Source: arxiv - Categories: quant-ph, cs.AI, cs.LG - PDF: https://arxiv.org/pdf/2604.06135v1 - Summary: Efficient data loading remains a bottleneck for near-term quantum machine-learning. Existing schemes (angle, amplitude, and basis encoding) either underuse the exponential Hilbert-space capacity or require circuit depths that exceed the coherence budgets of noisy intermediate-scale quantum hardware. We introduce Shot-Based Quantum Encoding (SBQE), a data embedding strategy that distributes the hardware's native resource, shots, according to a data-dependent classical distribution over multiple initial quantum states. By treating the shot counts as a learnable degree of freedom, SBQE produces a mixed-state representation whose expectation values are linear in the classical probabilities and can therefore be composed with non-linear activation functions. We show that SBQE is structurally equivalent to a multilayer perceptron whose weights are realised by quantum circuits, and we describe a hardware-compatible implementation protocol. Benchmarks on Fashion MNIST and Semeion handwritten digits, with ten independent initialisations per model, show that SBQE achieves 89.1% +/- 0.9% test accuracy on Semeion (reducing error by 5.3% relative to amplitude encoding and matching a width-matched classical network) and 80.95% +/- 0.10% on Fashion MNIST (exceeding amplitude encoding by +2.0% and a linear multilayer perceptron by +1.3%), all without any data-encoding gates. 9. [Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents](https://arxiv.org/abs/2604.06132v1) - Published: 2026-04-08 01:43 - Authors: Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, et al. - Source: arxiv - Categories: cs.AI - PDF: https://arxiv.org/pdf/2604.06132v1 - Summary: Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable. 10. [Gym-Anything: Turn any Software into an Agent Environment](https://arxiv.org/abs/2604.06126v1) - Published: 2026-04-08 01:38 - Authors: Pranjal Aggarwal, Graham Neubig, Sean Welleck - Source: arxiv - Categories: cs.LG, cs.AI - PDF: https://arxiv.org/pdf/2604.06126v1 - Summary: Computer-use agents hold the promise of assisting in a wide range of digital economic activities. However, current research has largely focused on short-horizon tasks over a limited set of software with limited economic value, such as basic e-commerce and OS-configuration tasks. A key reason is that creating environments for complex software requires significant time and human effort, and therefore does not scale. To address this, we introduce Gym-Anything, a framework for converting any software into an interactive computer-use environment. We frame environment creation itself as a multi-agent task: a coding agent writes setup scripts, downloads real-world data, and configures the software, while producing evidence of correct setup. An independent audit agent then verifies evidence for the environment setup against a quality checklist. Using a taxonomy of economically valuable occupations grounded in U.S. GDP data, we apply this pipeline to 200 software applications with broad occupational coverage. The result is CUA-World, a collection of over 10K long-horizon tasks spanning domains from medical science and astronomy to engineering and enterprise systems, each configured with realistic data along with train and test splits. CUA-World also includes CUA-World-Long, a challenging long-horizon benchmark with tasks often requiring over 500 steps, far exceeding existing benchmarks. Distilling successful trajectories from the training split into a 2B vision-language model outperforms models 2$\times$ its size. We also apply the same auditing principle at test time: a separate VLM reviews completed trajectories and provides feedback on what remains, improving Gemini-3-Flash on CUA-World-Long from 11.5% to 14.0%. We release all code, infrastructure, and benchmark data to facilitate future research in realistic computer-use agents. 11. [Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery](https://arxiv.org/abs/2604.06124v1) - Published: 2026-04-08 01:36 - Authors: Hao Chen, Fang Qiu, Fangchao Dong, Defei Yang, Eve Bohnett, Li An - Source: arxiv - Categories: cs.CV, cs.AI - PDF: https://arxiv.org/pdf/2604.06124v1 - Summary: This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its practical utility using a real drone-collected dataset. A thermal dataset was developed from drone-collected imagery and was used to fine-tune VLMs through multimodal projector alignment, enabling the transfer of information from RGB-based visual representations to thermal radiometric inputs. Three representative models, including InternVL3-8B-Instruct, Qwen2.5-VL-7B-Instruct, and Qwen3-VL-8B-Instruct, were benchmarked under both closed-set and open-set prompting conditions for species recognition and instance enumeration. Among the tested models, Qwen3-VL-8B-Instruct with open-set prompting achieved the best overall performance, with F1 scores of 0.935 for deer, 0.915 for rhino, and 0.968 for elephant, and within-1 enumeration accuracies of 0.779, 0.982, and 1.000, respectively. In addition, combining thermal imagery with simultaneously collected RGB imagery enabled the model to generate habitat-context information, including land-cover characteristics, key landscape features, and visible human disturbance. Overall, the findings demonstrate that lightweight projector-based adaptation provides an effective and practical route for transferring RGB-pretrained VLMs to thermal drone imagery, expanding their utility from object-level recognition to habitat-context interpretation in ecological monitoring. 12. [A Large-Scale Empirical Comparison of Meta-Learners and Causal Forests for Heterogeneous Treatment Effect Estimation in Marketing Uplift Modeling](https://arxiv.org/abs/2604.06123v1) - Published: 2026-04-08 01:35 - Authors: Aman Singh - Source: arxiv - Categories: stat.CO, cs.LG, econ.EM, stat.ME - PDF: https://arxiv.org/pdf/2604.06123v1 - Summary: Estimating Conditional Average Treatment Effects (CATE) at the individual level is central to precision marketing, yet systematic benchmarking of uplift modeling methods at industrial scale remains limited. We present UpliftBench, an empirical evaluation of four CATE estimators: S-Learner, T-Learner, X-Learner (all with LightGBM base learners), and Causal Forest (EconML), applied to the Criteo Uplift v2.1 dataset comprising 13.98 million customer records. The near-random treatment assignment (propensity AUC = 0.509) provides strong internal validity for causal estimation. Evaluated via Qini coefficient and cumulative gain curves, the S-Learner achieves the highest Qini score of 0.376, with the top 20% of customers ranked by predicted CATE capturing 77.7% of all incremental conversions, a 3.9x improvement over random targeting. SHAP analysis identifies f8 as the dominant heterogeneous treatment effect (HTE) driver among the 12 anonymized covariates. Causal Forest uncertainty quantification reveals that 1.9% of customers are confident persuadables (lower 95% CI > 0) and 0.1% are confident sleeping dogs (upper 95% CI < 0). Our results provide practitioners with evidence-based guidance on method selection for large-scale uplift modeling pipelines. 13. [ACE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments](https://arxiv.org/abs/2604.06111v1) - Published: 2026-04-08 01:21 - Authors: Wang Yang, Chaoda Song, Xinpeng Li, Debargha Ganguly, Chuang Ma, Shouren Wang, et al. - Source: arxiv - Categories: cs.AI, cs.CL - PDF: https://arxiv.org/pdf/2604.06111v1 - Summary: Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To address these issues, we propose ACE-Bench built around a unified grid-based planning task, where agents must fill hidden slots in a partially completed schedule subject to both local slot constraints and global constraints. Our benchmark offers fine-grained control through two orthogonal axes: Scalable Horizons, controlled by the number of hidden slots $H$, and Controllable Difficulty, governed by a decoy budget $B$ that determines the number of globally misleading decoy candidates. Crucially, all tool calls are resolved via static JSON files under a Lightweight Environment design, eliminating setup overhead and enabling fast, reproducible evaluation suitable for training-time validation. We first validate that H and B provide reliable control over task horizon and difficulty, and that ACE-Bench exhibits strong domain consistency and model discriminability. We then conduct comprehensive experiments across 13 models of diverse sizes and families over 6 domains, revealing significant cross-model performance variation and confirming that ACE-Bench provides interpretable and controllable evaluation of agent reasoning. 14. [Artificial Intelligence and the Structure of Mathematics](https://arxiv.org/abs/2604.06107v1) - Published: 2026-04-08 01:19 - Authors: Maissam Barkeshli, Michael R. Douglas, Michael H. Freedman - Source: arxiv - Categories: cs.AI, math.HO, math.LO - PDF: https://arxiv.org/pdf/2604.06107v1 - Summary: Recent progress in artificial intelligence (AI) is unlocking transformative capabilities for mathematics. There is great hope that AI will help solve major open problems and autonomously discover new mathematical concepts. In this essay, we further consider how AI may open a grand perspective on mathematics by forging a new route, complementary to mathematical\textbf{ logic,} to understanding the global structure of formal \textbf{proof}\textbf{s}. We begin by providing a sketch of the formal structure of mathematics in terms of universal proof and structural hypergraphs and discuss questions this raises about the foundational structure of mathematics. We then outline the main ingredients and provide a set of criteria to be satisfied for AI models capable of automated mathematical discovery. As we send AI agents to traverse Platonic mathematical worlds, we expect they will teach us about the nature of mathematics: both as a whole, and the small ribbons conducive to human understanding. Perhaps they will shed light on the old question: "Is mathematics discovered or invented?" Can we grok the terrain of these \textbf{Platonic worlds}? 15. [JUÁ - A Benchmark for Information Retrieval in Brazilian Legal Text Collections](https://arxiv.org/abs/2604.06098v1) - Published: 2026-04-08 01:10 - Authors: Jayr Pereira, Leandro Fernandes, Erick de Brito, Roberto Lotufo, Luiz Bonifacio - Source: arxiv - Categories: cs.IR, cs.CL - PDF: https://arxiv.org/pdf/2604.06098v1 - Summary: Legal information retrieval in Portuguese remains difficult to evaluate systematically because available datasets differ widely in document type, query style, and relevance definition. We present \textsc{JUÁ}, a public benchmark for Brazilian legal retrieval designed to support more reproducible and comparable evaluation across heterogeneous legal collections. More broadly, \textsc{JUÁ} is intended not only as a benchmark, but as a continuous evaluation infrastructure for Brazilian legal IR, combining shared protocols, common ranking metrics, fixed splits when applicable, and a public leaderboard. The benchmark covers jurisprudence retrieval as well as broader legislative, regulatory, and question-driven legal search. We evaluate lexical, dense, and BM25-based reranking pipelines, including a domain-adapted Qwen embedding model fine-tuned on \textsc{JUÁ}-aligned supervision. Results show that the benchmark is sufficiently heterogeneous to distinguish retrieval paradigms and reveal substantial cross-dataset trade-offs. Domain adaptation yields its clearest gains on the supervision-aligned \textsc{JUÁ-Juris} subset, while BM25 remains highly competitive on other collections, especially in settings with strong lexical and institutional phrasing cues. Overall, \textsc{JUÁ} provides a practical evaluation framework for studying legal retrieval across multiple Brazilian legal domains under a common benchmark design. ## Vision 1. [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://arxiv.org/abs/2604.06168v1) - Published: 2026-04-08 01:59 - Authors: Haoyu Zhen, Zixian Gao, Qiao Sun, Yilin Zhao, Yuncong Yang, Yilun Du, et al. - Source: arxiv - Categories: cs.CV, cs.RO - PDF: https://arxiv.org/pdf/2604.06168v1 - Summary: World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning. 2. [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://arxiv.org/abs/2604.06161v1) - Published: 2026-04-08 01:56 - Authors: Zhengming Yu, Li Ma, Mingming He, Leo Isikdogan, Yuancheng Xu, Dmitriy Smirnov, et al. - Source: arxiv - Categories: cs.CV, cs.AI, cs.GR - PDF: https://arxiv.org/pdf/2604.06161v1 - Summary: Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization. This loss of highlight and shadow detail precludes mapping accurate luminance to HDR displays and limits meaningful re-exposure in post-production workflows. Although techniques have been proposed to convert LDR images to HDR through dynamic range expansion, they struggle to restore realistic detail in the over- and underexposed regions. To address this, we present DiffHDR, a framework that formulates LDR-to-HDR conversion as a generative radiance inpainting task within the latent space of a video diffusion model. By operating in Log-Gamma color space, DiffHDR leverages spatio-temporal generative priors from a pretrained video diffusion model to synthesize plausible HDR radiance in over- and underexposed regions while recovering the continuous scene radiance of the quantized pixels. Our framework further enables controllable LDR-to-HDR video conversion guided by text prompts or reference images. To address the scarcity of paired HDR video data, we develop a pipeline that synthesizes high-quality HDR video training data from static HDRI maps. Extensive experiments demonstrate that DiffHDR significantly outperforms state-of-the-art approaches in radiance fidelity and temporal stability, producing realistic HDR videos with considerable latitude for re-exposure. 3. [MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control](https://arxiv.org/abs/2604.06156v1) - Published: 2026-04-08 01:55 - Authors: Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, et al. - Source: arxiv - Categories: cs.CV, cs.AI, cs.CL - PDF: https://arxiv.org/pdf/2604.06156v1 - Summary: MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency. 4. [Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery](https://arxiv.org/abs/2604.06124v1) - Published: 2026-04-08 01:36 - Authors: Hao Chen, Fang Qiu, Fangchao Dong, Defei Yang, Eve Bohnett, Li An - Source: arxiv - Categories: cs.CV, cs.AI - PDF: https://arxiv.org/pdf/2604.06124v1 - Summary: This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its practical utility using a real drone-collected dataset. A thermal dataset was developed from drone-collected imagery and was used to fine-tune VLMs through multimodal projector alignment, enabling the transfer of information from RGB-based visual representations to thermal radiometric inputs. Three representative models, including InternVL3-8B-Instruct, Qwen2.5-VL-7B-Instruct, and Qwen3-VL-8B-Instruct, were benchmarked under both closed-set and open-set prompting conditions for species recognition and instance enumeration. Among the tested models, Qwen3-VL-8B-Instruct with open-set prompting achieved the best overall performance, with F1 scores of 0.935 for deer, 0.915 for rhino, and 0.968 for elephant, and within-1 enumeration accuracies of 0.779, 0.982, and 1.000, respectively. In addition, combining thermal imagery with simultaneously collected RGB imagery enabled the model to generate habitat-context information, including land-cover characteristics, key landscape features, and visible human disturbance. Overall, the findings demonstrate that lightweight projector-based adaptation provides an effective and practical route for transferring RGB-pretrained VLMs to thermal drone imagery, expanding their utility from object-level recognition to habitat-context interpretation in ecological monitoring. 5. [SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation](https://arxiv.org/abs/2604.06113v1) - Published: 2026-04-08 01:24 - Authors: Hiba Dahmani, Nathan Piasco, Moussab Bennehar, Luis Roldão, Dzmitry Tsishkou, Laurent Caraffa, et al. - Source: arxiv - Categories: cs.CV - PDF: https://arxiv.org/pdf/2604.06113v1 - Summary: Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing solutions either rely on image or video generative models distilled to 3D space, harming the geometric coherence and restricting the rendering to training views, or are limited to small-scale 3D scene or object-centric generation. In this work, we propose a 3D generative framework based on $Σ$-Voxfield grid, a discrete representation where each occupied voxel stores a fixed number of colorized surface samples. To generate this representation, we train a semantic-conditioned diffusion model that operates on local voxel neighborhoods and uses 3D positional encodings to capture spatial structure. We scale to large scenes via progressive spatial outpainting over overlapping regions. Finally, we render the generated $Σ$-Voxfield grid with a deferred rendering module to obtain photorealistic images, enabling large-scale multiview-consistent 3D scene generation without per-scene optimization. Extensive experiments show that our approach can generate diverse large-scale urban outdoor scenes, renderable into photorealistic images with various sensor configurations and camera trajectories while maintaining moderate computation cost compared to existing approaches. 6. [Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning](https://arxiv.org/abs/2604.06079v1) - Published: 2026-04-08 00:58 - Authors: Juekai Lin, Yun Zhu, Honglin Lin, Sijing Li, Tianwei Lin, Zheng Liu, et al. - Source: arxiv - Categories: cs.CV, cs.AI - PDF: https://arxiv.org/pdf/2604.06079v1 - Summary: Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct. 7. [CoStream: Codec-Guided Resource-Efficient System for Video Streaming Analytics](https://arxiv.org/abs/2604.06036v1) - Published: 2026-04-08 00:31 - Authors: Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park, Shivaraman Nitin, Luo Tao, et al. - Source: arxiv - Categories: cs.DC, cs.CV, cs.LG - PDF: https://arxiv.org/pdf/2604.06036v1 - Summary: Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video streams, but they target either the vision transformer (ViT) or the LLM with a limited view, leaving end-to-end opportunities untapped. Moreover, existing methods incur significant overhead to identify redundancy, either through offline profiling and training or costly online computation, making them ill-suited for dynamic real-time streams. We present CoStream, a codec-guided streaming video analytics system built on a key observation that video codecs already extract the temporal and spatial structure of each stream as a byproduct of compression. CoStream treats this codec metadata as a low-cost runtime signal to unify optimization across video decoding, visual processing, and LLM prefilling, with transmission reduction as an inherent benefit of operating directly on compressed bitstreams. This drives codec-guided patch pruning before ViT encoding and selective key-value cache refresh during LLM prefilling, both of which are fully online and do not require offline training. Experiments show that CoStream achieves up to 3x throughput improvement and up to 87% GPU compute reduction over state-of-the-art baselines, while maintaining competitive accuracy with only 0-8% F1 drop. 8. [OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control](https://arxiv.org/abs/2604.06010v1) - Published: 2026-04-08 00:06 - Authors: Yukun Wang, Ruihuang Li, Jiale Tao, Shiyuan Yang, Liyi Chen, Zhantao Yang, et al. - Source: arxiv - Categories: cs.CV - PDF: https://arxiv.org/pdf/2604.06010v1 - Summary: Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this work, we introduce OmniCamera, a unified framework designed to explicitly disentangle and command these two dimensions. This compositional approach enables flexible video generation by allowing arbitrary pairings of camera and content conditions, unlocking unprecedented creative control. To overcome the fundamental challenges of modality conflict and data scarcity inherent in such a system, we present two key innovations. First, we construct OmniCAM, a novel hybrid dataset combining curated real-world videos with synthetic data that provides diverse paired examples for robust multi-task learning. Second, we propose a Dual-level Curriculum Co-Training strategy that mitigates modality interference and synergistically learns from diverse data sources. This strategy operates on two levels: first, it progressively introduces control modalities by difficulties (condition-level), and second, trains for precise control on synthetic data before adapting to real data for photorealism (data-level). As a result, OmniCamera achieves state-of-the-art performance, enabling flexible control for complex camera movements while maintaining superior visual quality. 9. [HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation](https://arxiv.org/abs/2604.05961v1) - Published: 2026-04-07 22:55 - Authors: Tao Hu, Varun Jampani - Source: arxiv - Categories: cs.CV - PDF: https://arxiv.org/pdf/2604.05961v1 - Summary: Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In this paper, we propose a new framework for human video generation, HumANDiff, which enhances the human motion control with three key designs: 1) Articulated motion-consistent noise sampling that correlates the spatiotemporal distribution of latent noise and replaces the unstructured random Gaussian noise with 3D articulated noise sampled on the dense surface manifold of a statistical human body template. It inherits body topology priors for spatially and temporally consistent noise sampling. 2) Joint appearance-motion learning that enhances the standard training objective of video diffusion models by jointly predicting pixel appearances and corresponding physical motions from the articulated noises. It enables high-fidelity human video synthesis, e.g., capturing motion-dependent clothing wrinkles. 3) Geometric motion consistency learning that enforces physical motion consistency across frames via a novel geometric motion consistency loss defined in the articulated noise space. HumANDiff enables scalable controllable human video generation by fine-tuning video diffusion models with articulated noise sampling. Consequently, our method is agnostic to diffusion model design, and requires no modifications to the model architecture. During inference, HumANDiff enables image-to-video generation within a single framework, achieving intrinsic motion control without requiring additional motion modules. Extensive experiments demonstrate that our method achieves state-of-the-art performance in rendering motion-consistent, high-fidelity humans with diverse clothing styles. Project page: https://taohuumd.github.io/projects/HumANDiff/ 10. [Multi-Modal Landslide Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Multi-Encoder Vision Transformers and Ensemble Learning](https://arxiv.org/abs/2604.05959v1) - Published: 2026-04-07 22:51 - Authors: Ioannis Nasios - Source: arxiv - Categories: cs.CV, cs.LG - PDF: https://arxiv.org/pdf/2604.05959v1 - Summary: Landslides represent a major geohazard with severe impacts on human life, infrastructure, and ecosystems, underscoring the need for accurate and timely detection approaches to support disaster risk reduction. This study proposes a modular, multi-model framework that fuses Sentinel-2 optical imagery with Sentinel-1 Synthetic Aperture Radar (SAR) data, for robust landslide detection. The methodology leverages multi-encoder vision transformers, where each data modality is processed through separate lightweight pretrained encoders, achieving strong performance in landslide detection. In addition, the integration of multiple models, particularly the combination of neural networks and gradient boosting models (LightGBM and XGBoost), demonstrates the power of ensemble learning to further enhance accuracy and robustness. Derived spectral indices, such as NDVI, are integrated alongside original bands to enhance sensitivity to vegetation and surface changes. The proposed methodology achieves a state-of-the-art F1 score of 0.919 on landslide detection, addressing a patch-based classification task rather than pixel-level segmentation and operating without pre-event Sentinel-2 data, highlighting its effectiveness in a non-classical change detection setting. It also demonstrated top performance in a machine learning competition, achieving a strong balance between precision and recall and highlighting the advantages of explicitly leveraging the complementary strengths of optical and radar data. The conducted experiments and research also emphasize scalability and operational applicability, enabling flexible configurations with optical-only, SAR-only, or combined inputs, and offering a transferable framework for broader natural hazard monitoring and environmental change applications. Full training and inference code can be found in https://github.com/IoannisNasios/sentinel-landslide-cls.