SLVR (Structured Latent Visual Reasoning) is a training framework that blends explicit chain-of-thought with latent reasoning for multimodal large language models. It organizes reasoning into typed latent stages—planning, grounding, evidence selection, and integration—each supervised by corresponding signals such as plans, bounding boxes, visual evidence, and final rationales. Built on Qwen2.5‑VL‑7B, SLVR consistently improves performance on multimodal reasoning benchmarks, achieving significant gains on MMVP, BLINK Relation, V*, MathVista, and ChartQA.
By Albert Gao, Bing Xue, Andrea Zanette
The paper surveys how large language models (LLMs) are being used in hardware verification, covering tasks such as assertion generation, testbench creation, bug localization, and formal reasoning. It categorizes the literature by methodology, verification goal, tool interaction, benchmarks, and evaluation metrics, and distinguishes between inference-time techniques (prompting, retrieval, structured reasoning, agentic workflows) and training-time adaptation. The authors highlight that LLMs excel as semantic reasoning, search, and orchestration components within verification workflows, yet emphasize the need for semantic alignment, scalable integration, generalization, and rigorous evaluation to ensure true verification correctness.
By Hao Zheng, Jaime Rafael Imperial, Bardia Nadimi, Xiangfei Kong
arXiv:2610. 10597v1 Announce Type: cross Abstract: Public leaderboards for AI models are read continuously, and attackers can see every published standing.
By Hamed Khosravi, Xiaoming Huo
The study investigates whether large language models (LLMs) have improved in screening systematic reviews (SRs) within software engineering. Using the SESR‑Eval benchmark and a new smaller dataset, the authors evaluated eight recent LLMs and found only marginal performance gains over older models (average MCC rose from 0.347 to 0.365). The research also examined prompt variations, inter‑model agreement, and the impact of refining inclusion/exclusion criteria, concluding that LLMs still fall short of replacing human reviewers and that future work should explore agent‑based methods, prompt engineering, and further criteria refinement.
By Aleksi Huotala, Miikka Kuutila, Mika M\"antyl\"a
The paper introduces Transformed Samplers with Variance Reduction, a method that extends exact control variate solutions from simple reference densities to general target distributions by learning a bijective change of variables, such as a normalizing flow. By training the flow to map the target close to the reference in latent space, the authors show that Markov kernels and their Poisson solutions transform accordingly, enabling explicit control variates in the latent space. The resulting estimator is consistent under mild tail conditions, and the approach also applies to importance sampling, with experiments demonstrating competitive performance against state‑of‑the‑art samplers and control variates.
By Siran Liu, Michalis Tisias, Petros Dellaportas
iCATS introduces a training‑free sparse attention mechanism for Diffusion Transformers that accelerates video generation by reducing computations. It improves importance estimation by clustering query‑key dot‑product interactions and reformulates the objective as a quadratic form for low‑cost computation. The method also adapts sparsity dynamically across denoising timesteps using an SNR‑guided schedule and employs a tail‑merging strategy to enhance GPU kernel utilization, achieving significant speedups while maintaining high PSNR scores.
By Chengfeng Han, Baole Ai, Xianlu Bian, Jie Yao, Zilong Huang, Ang Wang, Dandan Ding
PathLang is a new, language‑centered benchmark for vision‑language models in computational pathology. It keeps the underlying pathology slides, ground‑truth labels, and image‑text evaluation direction constant while systematically varying the diagnostic language used in prompts, reflecting how pathologists actually rephrase diagnoses. The benchmark covers four task families—zero‑shot classification with image‑text alignment, cross‑modal retrieval, paraphrase robustness, and open‑vocabulary diagnosis retrieval—and evaluates nine VLMs across five public datasets spanning four organs.
By Fanqi Cheng, Kuo Gong, Shangke Liu, Beidi Zhao, Junchao Zhu, Zheyu Zhu, Leiyue Zhao, Fengbei Liu, John Cannon, Gang Wang, Zu-hua Gao, Kenji Ikemura, Yihe Yang, Yaohong Wang, Yuankai Huo, Xiaoxiao Li, Mert R. Sabuncu, Ruining Deng
Parametric Trajectory Distillation (PTD) is a new method for few-step video generation that allows a student model to learn teacher trajectory segments as polynomials, adapting curvature to the student’s predictive capacity. PTD improves dynamic quality and naturalness on the Wan2.1-14B model, outperforming the previous best trajectory-only method, PDD, and also enhances diversity and naturalness on the 33B MiniMax-H3 model compared to LightX2V Turbo. Human preference studies show PTD receiving 55.1% and 63.4% preference shares over PDD and LightX2V Turbo respectively.
By Lan Feng, Peter Karkus, Maximilian Igl, Julius Berner, Yuxiao Chen, Shuhan Tan, Alexandre Alahi, Boris Ivanovic, Marco Pavone
SV-TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of dense reconstruction in token‑selection methods. By integrating this primitive into a temporal action detection framework, the approach cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, it surpasses prior state‑of‑the‑art performance at roughly half the computational cost and naturally supports auxiliary task tokens for improved fine‑grained assembly detection on ATTACH.
By Ricardo Pizarro, Roberto Valle, Jos\'e M. Buenaposada, Luis M. Bergasa, Luis Baumela
The paper introduces a new benchmark for evaluating holistic, semantics-aware co‑speech gesture generation, combining 13 objective metrics and a novel Semantic Gesture Preservation (SGP) metric that measures how well ground‑truth semantic gestures are retained. A perceptual study with 101 participants rates generated gestures on five dimensions, revealing that SGP aligns with speech‑aware human judgments while other metrics do not. Composite metrics tailored to each dimension further improve alignment, especially for animation errors and content match, underscoring the need to validate objective metrics against human perception.
By Nick Milkin, Lanmiao Liu, Esam Ghaleb, Asli Ozyurek, Zerrin Yumak
The paper introduces EUA‑Cal, a calibration method that preserves the early‑training uncertainty of deep neural networks. By regularizing predictions and feature prototypes based on the early model, EUA‑Cal mitigates overconfidence while maintaining accuracy. Experiments on image classification and multiple‑choice question answering across eight models show EUA‑Cal outperforms existing calibration techniques.
By Yutong Xie, Jiawei Tang, Zhenglin Hua, Yuxiang Ma, Si Qin, Yaxin Hou, Hui Liu, Junhui Hou, Yuheng Jia
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
By Yicheng Xue, Han Wu, Jufeng Yang, Minjing Dong, Xinghao Chen, Hanting Chen, Jianyuan Guo
Slot3R introduces a set‑associative spatial memory that allows multiple states to coexist at the same 3D location, addressing the limitation of Point3R where spatial proximity forces merging of distinct observations. By keeping the pretrained Point3R backbone frozen and adding a bounded sparse readout, Slot3R improves point‑cloud accuracy by up to 72% on benchmark datasets and reduces trajectory error across pose benchmarks, while maintaining real‑time performance up to 1000 frames without exhausting memory.
By Xiyuan Zhang, Yanming Yang, Kaiyuan Xu, Ruibo Li, Chi Zhang
The paper investigates whether in‑domain training alone can enable multimodal large language models (MLLMs) to perform fine‑grained industrial anomaly understanding (MM‑IAU). It shows that even specialized MLLMs fail to match human experts on defect localization and detection, and that combining different MLLMs does not eliminate this shortfall. To address this, the authors propose SiGMA, a spatially grounded multi‑agent framework that splits tasks among heterogeneous MLLM agents and a dedicated visual defect expert, achieving 85.2% accuracy on the MMAD benchmark—close to human performance and surpassing the best trained specialist.
By Xingwu Zhang, Duanyang Du, Huiling Zhu, Jiayue Dai, Yixiao Liu, Guozhi Liu, Zhihan Zhang, Zijun Long
The paper introduces RISEBench and its expanded version RISEBench++, a benchmark for evaluating reasoning-informed visual editing (RISE). RISEBench++ categorizes tasks into six reasoning dimensions—Temporal, Causal, Spatial, Logical, Counterfactual, and Hybrid—decomposed into 12 subcategories and 65 fine-grained task types, and includes 1,000 human‑annotated test cases in English and Chinese. The authors also present RISE‑Agent, a training‑free framework that integrates reasoning‑driven planning, tool‑augmented execution, and verifier‑guided refinement, outperforming most existing approaches on diverse RISE tasks.
By Xue Yang, Peiyuan Zhang, Yilun Zhu, Qihao Yang, Mingxin Liu, Xiangyu Zhao, Ziqian Fan, Zhaokai Wang, Yan Li, Yifan Yang, Xu Yang, Xiaosong Jia, Yue Zhou, Zhihang Zhong, Junchi Yan
GenIA is a framework that aligns generative 3D foundation models with test‑time observations, improving pose estimation and reconstruction from monocular, multi‑view, and dynamic inputs. It derives translation and scale from geometry, retains learned rotation priors, and aligns appearance using visibility‑biased attention, cross‑observation fusion, and differentiable rendering guidance during denoising. An optional post‑denoising refinement further adapts appearance latents and object placement, and the method also supports externally supplied geometry for dynamic objects, achieving better results than recent optimization‑based and image‑to‑3D methods on synthetic and real benchmarks.
By Stefano Esposito, Naama Pearl, Polina Karpikova, Samuel Rota Bul\`o, Lorenzo Porzi, Peter Kontschieder, Andreas Geiger, Jonathon Luiten
OneSearch‑VL is a unified multimodal deep research agent that handles single‑image, multi‑image, and video tasks by leveraging a Visually Grounded Evidence Graph (VGEG) to encode dependencies among visual anchors, entity relations, facts, and answer‑producing operations. The VGEG‑based data engine builds and verifies questions, filters expert trajectories, and supports supervised fine‑tuning (SFT) and reinforcement learning (RL) with the Evidence‑aware Visual‑Grounded Rubric reward (EVGR). Experiments demonstrate that OneSearch‑VL‑8B outperforms Qwen3‑VL‑8B with tool access by 20.2 and 17.6 percentage points on new multimodal benchmarks, while also achieving significant gains across seven image benchmarks and VideoDR.
By Hongyu Li, Manyuan Zhang, Kaituo Feng, Shu Chen, Dian Zheng, Hao Li, Hao Yu, Zhangquan Chen, Zoey Guo, Ray Zhang, Shaofei Huang, Tianrui Hui, Linjiang Huang, Si Liu
OmniCapBench is a new deep‑structured evaluation framework for audio‑visual captioning that replaces free‑form text predictions with sets of atomic, verifiable units across entity references, visual shots, and audio events. It uses deterministic constraint checks and localized LLM‑based semantic comparisons to provide reliable, fine‑grained scoring. With 786 densely annotated videos, the benchmark can distinguish perception errors such as temporal grounding failures, identity drift, cross‑modal misalignment, and hallucinations, revealing that current multimodal large language models excel at local perception but struggle with long‑horizon audio‑visual reasoning.
By Zhongyu Yang, Jiale Tao, Ruitao Chen, Zuhao Yang, Yingfang Yuan, Xueliang Zhao, Auden, Kai Wang, Shuai Shao, Biao Wang, Steve Yves, Qinglin Lu
The paper introduces EpiReal-Bench, a benchmark of 10,000 false-claim prompts and corresponding images designed to test visual misinformation risks in commercial image generators. It also presents EpiReal-Attack, a black-box optimization framework that can bypass alignment safeguards, increasing the success rate of generating misleading images from 70% to 95%. Experiments on four commercial models show that these generators can produce credible visual evidence for false claims, highlighting a blind spot in current alignment methods.
By Zeyu Ye, Yanchun Li, Sibei He, Meng Xie, Hangtao Zhang, Xianlong Wang, Li Zeng, Jiahao Chen, Yichen Wang, Junhui Wang, Ziqi Zhou
WARP-VLA is a Vision‑Language‑Action model designed to be robust to variations in wrist‑camera viewpoints. It uses a Mixture‑of‑Experts architecture where each expert learns a view‑specific feature transformation, and a router selects the appropriate expert based on implicit view cues, eliminating the need for explicit camera extrinsic parameters. Experiments on the LIBERO benchmark show that WARP‑VLA doubles the success rate of pi‑0.5 from 39.2% to 78.3% under wrist‑view perturbations, and real‑robot tests confirm that the simulation‑learned adaptation transfers to diverse deployment settings.
By Junmyeong Lee, Dongmin Shin, Min-Gyu Park, Wooseok Jeon, Inho Chang, Hae-Gon Jeon