Transformer
-
LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends
Abstract
Visual agents need to coordinate reasoning and action while their environment evolves during inference. We introduce LOLPlay, a benchmark in native League of Legends with 36 champion-specific tasks spanning resource management, combat, cooperation, and objectives. Agents interact through screenshots and mouse-keyboard actions; automated initialization and 82 executable subgoal checks distinguish partial progress from completion. Across 324 task evaluations of three models at three reasoning-effort settings, GPT-6 Astra achieves the highest task success rate of 25.0% at low and medium effort, and the highest subgoal success rate of 40.3% at medium effort. However, high effort improves neither metric over low effort for any model. For Astra, longer requests leave fewer interaction rounds, suggesting a cost to additional reasoning in real-time control. Trajectories reveal incomplete subgoal composition and actions executing after the observed scene changes, motivating agents that combine visual reasoning with timely action.
Abstract (translated)
URL
https://arxiv.org/abs/2611.03685
PDF
-
TraceKV: Policy-Preserving Low-Rank KV Cache Compression for Reasoning Vision-Language Models
2026-11-11 14:54:19Ke Li, Zishan Shao, Yiran ChenAbstract
Reasoning vision-language models (VLMs) impose substantial KV cache demands from both large multimodal contexts and growing reasoning traces. Low-rank KV compression has emerged as a promising paradigm that stores low-dimensional latents of KV states and can be combined with quantization. However, existing low-rank methods often induce growing predictive policy drift from the dense model when compressing reasoning KV states, resulting in reasoning failures. We identify two key causes of this degradation: calibration-state mismatch between static contexts and on-policy reasoning states, and unequal error sensitivity across KV states. To address these challenges, we propose TraceKV, a training-free low-rank KV compression framework that unifies on-policy calibration, sensitivity-aware SVD, and global rank allocation under a single policy-preserving principle, substantially reducing policy-KL divergence during reasoning. Experiments across multiple VLMs and visual reasoning benchmarks demonstrate superior accuracy--memory trade-offs, achieving near-lossless reasoning accuracy with 5.64$\times$ KV cache compression when combined with quantization. Optimized low-rank attention kernels further deliver up to 1.83$\times$ end-to-end decoding speedup. Code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15569
PDF
-
CARE-Drive: Coupled Alternating Refinement for Ego-trajectories
2026-11-11 11:39:00Xiao Ma, Yijun Chen, Zhiquan Hu, Jicheng Zhao, Yuming Li, Chuang DaiAbstract
Vision-language-action (VLA) models bring multimodal understanding and world knowledge to end-to-end autonomous driving. To further improve the quality of predicted trajectories, existing studies introduce candidate refinement, residual denoising, and token correction. However, these methods typically focus on unified refinement of the entire trajectory, paying limited attention to the distinct physical quantities and their interactions. We further investigate physical specialization and coordination in trajectory refinement, centering on position and heading for simpler and more intuitive correction modeling. To this end, we propose CARE-Drive (Coupled Alternating Refinement for Ego-trajectories), which decomposes trajectory refinement into waypoint residual correction and position-conditioned heading generation. Through imitation learning and a future-token auxiliary task, the backbone provides predictive representations and a base trajectory. The position expert predicts bounded metric waypoint residuals, while the heading expert reconstructs vehicle orientation from adjacent angular increments conditioned on the corrected path. With the backbone frozen, the two experts are optimized alternately through supervised initialization and reinforcement fine-tuning. This design simplifies refinement through clear physical specialization while preserving conditional coupling during prediction and optimization. On NAVSIM v1, CARE-Drive achieves 88.8 PDMS, improving by 2.4 points over the unrefined base trajectories generated by the same backbone. Ablation studies further support the effectiveness of specialized experts and staged training.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15360
PDF
-
HumanSightBench: A Benchmark for Human Visual Perception in MLLMs
2026-11-11 10:19:36Zixin Su, Yangguang Lin, Zegang Peng, Yuntong Sun, Xuanyi Wang, Jiahao Wang, Qiankai Xu, Bing Yuan, Jingjia Huang, Ruyang Liu, Yanxu Hu, Yufeng Zhou, Yi LinAbstract
Multimodal large language models (MLLMs) have demonstrated strong performance on knowledge-intensive and reasoning-based vision-language benchmark datasets, but still struggle to solve the visual questions that people can solve easily. Evaluating the differences between MLLMs and human-level visual perception is challenging due to end-to-end evaluation which combines various skills, or because we are uncertain if individual items are valid. Specifically, observed errors may reflect visual perception, language priors, background knowledge, question ambiguity, and underspecified answers. Our guideline for HumanSightBench is that we construct items that are human-easy by construction and model-hard by evaluation. HumanSightBench contains 2,876 visual questions with short answers across 7 top-level perceptual categories and 21 subcategories. We only include items that pass five inclusion gates: question clarity, answer uniqueness, visual grounding, human solvability, and text-only shortcut filtering. According to the protocol, errors are defined as incorrect answers on human-validated visual tasks with the evaluated interface. The inclusion gates are intended to reduce confounds from ambiguity and external knowledge. The best pass@3 score is 65.6% across eight evaluated MLLMs. No evaluated model exceeds 27.5% on Counting. These results identify capability gaps that are hidden by overall scores and can help future training experiments and held-out evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12305
PDF
-
Multi-head Quantum Neural Networks: Replacing Transformer Blocks with NISQ Modules inside a 30-Billion-Parameter LLM
2026-11-11 09:39:14Maforikan Amoussou, Borja Aizpurua, Sukhbinder Singh, Rom\'an Or\'us, Hans-Arno JacobsenAbstract
We introduce the multi-head quantum neural network (QNN), a quantum module compatible with noisy intermediate-scale quantum (NISQ) devices that can replace transformer blocks inside pre-trained large language models (LLMs) with little loss in accuracy and with far fewer parameters than the blocks it replaces. Encoding a model's $D$ hidden neurons into a qubit register is the obstacle: amplitude encoding scales poorly in circuit depth and angle encoding in qubit count, so neither is practical at production-scale width. We instead partition the hidden space into $k$ disjoint heads, angle-encode each into an $n_q$-qubit register, process the heads in parallel, and couple them through constrained classical linear layers, the mixers. Performing surgery on Qwen3-30B-A3B-Instruct-2507, we show that a single multi-head QNN with $145\,281$ trainable parameters ($D=2048$, $k=32$, $n_q=8$, $L=4$) can replace a contiguous span of eight transformer blocks, displacing $16.33\%$ of the model's parameters. Ablations show that, for a single replaced block, the quantum heads (circuits followed by a learned readout), and not the classical mixers alone, recover the displaced function, whereas for fused spans the mixers alone come within $1$-$3\%$ of the full module in perplexity. Whether this benefit is specific to trained, entangling quantum circuits is not established: controls that switch the entangler off (two seeds), or freeze the circuit at its initial or at uniformly random angles (one seed), beat the full module on held-out perplexity, and a parameter-matched classical multilayer perceptron remains a few percent ahead of the full module. We train classically with exact statevector simulation, then execute the quantum heads of our fusion checkpoints on a $156$-qubit IBM Heron processor, showing that NISQ-scale quantum modules can be installed in a production-scale LLM and run on hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15250
PDF
-
Towards Robust Vision-Language Reasoning: A Multi-Stage Optimization Pipeline with Masked Diffusion Model
2026-11-11 09:30:15Shunming Liu, Pei Huang, Yajing Sun, Huaxiao LiuAbstract
Discrete diffusion generation is emerging as a competitive alternative to autoregressive generation by denoising the entire token sequence through iterative refinement. Its global planning and progressive correction capabilities are particularly well suited to autonomous driving. However, transferring this generation paradigm from general-purpose settings to driving introduces substantial domain gaps in both training and inference. To unlock its potential, we propose a multi-stage optimization pipeline for standard vision-language model architectures, without auxiliary action experts or specialized mixture-of-experts Transformer, spanning post-training and inference. During supervised fine-tuning, we optimize the representation of planning inputs to suppress hallucinations in task responses. During reinforcement learning, we introduce metric-guided diversity filtering to identify stronger learning starting points and improve policy exploration. At inference time, we propose Dynamic Autonomous Driving Decoding (DAD), which adaptively adjusts decoding modes according to scene complexity. Based on this pipeline, we develop Masked Diffusion Drive (MD-Drive), improving its performance by 29.7\% over the unoptimized model. Experiments on the NAVSIM closed loop benchmark and the nuScenes and DriveCoT open loop datasets show that MD-Drive outperforms autoregressive VLM baselines with the same architecture, while achieving a more favorable balance between performance and computational cost than systems with different architectures through discrete diffusion training and inference.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15238
PDF
-
HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution
2026-11-11 08:20:21Haoran Luo, Shangkai Lin, Jinyang Wu, Xinliang Zhou, Luu Anh TuanAbstract
Reinforcement learning sharpens LLM reasoning, but parameter updates are expensive, forgetful, and opaque; training-free libraries swap gradients for a textual store but still use trajectory-level, correlation-based admission and flat structure. To address both, we propose HyperSkill, a Training-Free Omnimodal GRPO framework that keeps the backbone frozen and replaces gradient updates with auditable edits to a Hypergraph-Indexed Skill-Library, where skills are advantage-bearing nodes and compositions are hyperedges. It has three components: training-time distillation admits counterfactually checked skills and learns a protocol skill from failures; gated hypergraph retrieval injects advantage-ranked skills where a per-dataset gate admits them; and an execution protocol makes the frozen backbone commit to an answer. On 11 text, vision-language, and omnimodal benchmarks, HyperSkill is best or tied on every dataset and beats the best baseline by 13.0 average F1 points while keeping the backbone frozen. Our software and data are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15178
PDF
-
A frontier machine intelligence for human neuroimaging
2026-11-11 06:11:38Chenhui Zhao, Akshay Rao, Akhil Kondepudi, Yiwei Lyu, Xinhai Hou, Rikhil Seshadri, Cheng Jiang, Soumyanil Banerjee, Rushikesh Joshi, Samir Harake, Ashok Srinivasan, Shruti Mishra, Francisco Rivas-Rodriguez, Seunghong Rhee, Nathaniel Roddenberry, Neeraj Chaudhary, Zach Wilseck, Paul Park, Honglak Lee, Vikas Gulani, Aditya Pandey, Todd HollonAbstract
Medical imaging is essential for diagnosing disease, guiding treatment and monitoring patients over time. Although artificial intelligence has advanced image interpretation, existing medical models often address restricted tasks, while general-purpose proprietary models lack access to private clinical imaging required to achieve medical expertise. Developing models that can interpret complex examinations and communicate their findings in the context of clinical decisions remains a major challenge. Here, we show that Neuro-VL, a vision-language model trained on nearly one million neuroimaging studies from routine clinical care, can interpret complete imaging examinations and engage in natural language conversations about their findings. Across internal and international datasets, Neuro-VL outperformed frontier general-purpose and specialized medical models in diagnosing, localizing, and describing abnormalities, as well as generating comprehensive radiology reports. The model also compared serial examinations to assess disease progression and more reliably resisted misleading clinical assumptions than leading frontier models from OpenAI and Google. These results extend health system learning beyond individual predictions to interactive image interpretation and longitudinal disease monitoring. They demonstrate how the collective clinical experience of health systems can be used to develop medical AI with specialized expertise and broad clinical capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15094
PDF
-
A Time-Frequency-Condition Multimodal Fusion Foundation Model for Universal Rotating-Machinery Fault Diagnosis under Multi-Element Heterogeneous Scenarios
2026-11-11 05:25:10Xinyu Zou, Jian Ma, Liang Ma, Chen Lu, Tao Peng, Yingjie LiAbstract
Intelligent fault diagnosis models are typically developed for a single machine under a specific set of operating conditions, such that each new machine or condition requires retraining from scratch. This one-machine-one-model paradigm scales poorly. Although transfer learning and domain generalization can reduce the labeling burden, they primarily seek domain-invariant commonality, potentially discarding machine-specific characteristics that are critical for diagnosis. This paper proposes TFC-MMFD, a time-frequency-condition multimodal fusion foundation model for rotating-machinery fault diagnosis under multi-element heterogeneous scenarios. Statistical indicators, time-frequency images, vibration sequences, and textual machine and condition descriptions are tokenized into a unified language-like space, allowing inputs of different physical origin to be represented as a single sequence. A LLaMA backbone, together with cross-modal bidirectional attention and a Q-Former, then distills this sequence into fault-mode queries. Diagnosis is performed by matching these queries against natural-language fault-mode anchors rather than fixed class indices, while regression-adversarial condition disentanglement and condition-conditioned masked pre-training improve robustness to changing conditions. Across four progressive tasks on ten public bearing datasets spanning diverse bearing types, speeds, and loads, TFC-MMFD attains 99.40% accuracy and 99.16% macro-F1, maintains over 80% accuracy on most interpolated unseen conditions without adaptation, and improves from 20.26% to 95.63% accuracy on an unseen machine with only five labeled samples per class. It outperforms the strongest of eight domain-generalization baselines by 10.57 percentage points and compares favorably with a recent bearing foundation model while using less than half of its fine-tuning data.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15051
PDF
-
AutoQS: Automated Quantization Strategy Design with Large Language Models
2026-11-11 05:23:20Zhen Liu, Zhiqin Yang, Yonggang Zhang, Jianyi Liu, Jinjun Wang, Jingwen FuAbstract
Quantization reduces LLM deployment costs, but effective strategies must balance model quality and storage. LLM-driven search can automate strategy design through repeated proposal and evaluation. This process must identify useful strategies within a limited evaluation budget. The key challenge is that \textit{actual quantization is expensive, while inexpensive proxies may not reflect quantized-model performance.} To address this challenge, we present AutoQS, an \textbf{Auto}mated \textbf{Q}uantization \textbf{S}trategy Design with LLMs. AutoQS keeps weight precision fixed and searches group-size allocations across layers and operators under deployment constraints. Evaluation history guides coordinated LLM proposals, while deterministic validation ensures compatible allocations. An inexpensive quality proxy evaluates candidates, and an candidate repository retains alternative allocations to inform subsequent proposals. Periodic actual quantization complements these proxy evaluations with measured quality and checkpoint storage, providing feedback for further search within the evaluation budget. Experiments on Qwen2.5-7B-Instruct show that AutoQS improves seven-task average accuracy over uniform-group GPTQ and AWQ by 0.70 and 1.12 percentage points, respectively, at four-bit weight precision.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11975
PDF
-
SkinAdvisor: An AI-Driven Decision Framework for Skin Production Planning via Multi-Modal Transformer Sales Forecasting
2026-11-11 04:36:07Ge Fan, Kai Wang, Chaoyun Zhang, Yingjie Li, Yuze Liu, Junyang ChenAbstract
Skins, cosmetic in-game items, are a primary revenue stream for modern online games, yet production decisions (which skins to make, when to release, how to price) remain driven by intuition and retrospective analytics. We present SkinAdvisor, an AI-driven decision framework for skin production planning, powered by SkinCast, a deployed multi-modal Transformer forecasting 180-day per-day sales trajectories for unreleased skins. SkinCast couples four encoders: a pretrained Informer for player-preference time series, a pretrained Player-Hero-Skin graph embedder for relational priors, and two lightweight Transformers for skin attributes and release context, fused through a shared backbone with a local-plus-global day-x positional encoding and decoded by an N-layer Informer in a single non-autoregressive pass. SkinAdvisor plugs these forecasts into a serving pipeline (Select -> Fill -> Infer -> Sales -> ROI -> Ranking) that ranks candidate skins by forecast-based ROI and supports multi-candidate comparison. The system has been in production for a full release cycle. Offline experiments show SkinCast reduces RMSE by ~20% over the strongest baseline (Informer) and ~60% over classical methods; stress tests on a 16-core CPU server confirm p99 latency under 8ms and peak throughput above 1100 rps. We report two deployment lessons: order-of-magnitude accuracy suffices for production decisions, and pretrained embeddings can leak temporal information, requiring season-based splitting to prevent.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15023
PDF
-
Breaking Bad: 'Going Badly' Activations Drive Reward Hacking
2026-11-11 03:49:11Natalia Fischl-Lanzoni, Punya Syon Pandey, Merlin Stein, David Demitri AfricaAbstract
Humans often cheat when a task is going badly and a goal feels out of reach. We explore and validate an analogous idea in language models: they exhibit a similar internal pressure state that precedes reward hacking. Using everyday stories (crucially, without any hacking examples), we extract a task badness direction that rises as failures accumulate across three models we study (Qwen3.6-27B, GPT-OSS-20B, and Gemma-4-31B). On impossible or difficult coding tasks, task badness rises over the turns leading up to a hack. Further, subtracting the direction a moderate amount reduces cheating in Qwen, more than steering against desperation or task impossibility. Subtracting task badness by an even larger amount blinds the agent to its own failures, causing it to interpret failing tests as passing. However, the relationship to hacking differs across models: in GPT-OSS, the state separates hacking runs from honest solves but not honest failures. Our results suggest monitoring and mitigation strategies based on tracking this state of task badness. Further, as agents are set on more difficult and long-horizon tasks, states like this may push them toward illegible and obscured chain-of-thought, so oversight will be needed on internal representations such as this.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14996
PDF
-
Emergent Vision-Shaped Thinking in Text-Only Reasoning through Multimodal Training
2026-11-11 02:44:10Qi Zhang, Bohan Wang, Qianru Sun, Hanwang ZhangAbstract
Does multimodal training shape how a language model thinks, even when the input is text only? We test this with targeted causal ablations across 10 multimodal configurations from 6 model families, with matched text-only backbones and cross-family transfer controls. We contrast spatial-imagery tasks that invite mental scene construction with symbol-manipulation tasks solvable by symbolic rules alone. We identify a vision-language axis in hidden-state space and ablate its projection at inference. In Chameleon-7B, this ablation drops accuracy on BIG-Bench Hard (BBH) navigate by 27.6 pp while leaving boolean expressions intact (+5.6 pp), a 33.2 pp double dissociation. The effect is direction-specific and layer-localized, extends to mental-simulation tasks such as mental rotation, paper folding, and perspective taking, and is not explained by task difficulty, reasoning depth, or sequential update load. Together, these results reveal emergent vision-shaped thinking (EVT): text-only reasoning that causally recruits representations introduced or strengthened by vision-language training, without assuming an image-like internal format. The measured effect is spatially concentrated at 7-8B and broadens to non-spatial visual attribute binding in the tested 32B configuration. In dual-path unified models (BAGEL, Janus-Pro), the causal handle localizes to the generation pathway as a compact one-dimensional carrier. The understanding pathway also encodes spatial information in a higher-rank, probe-decodable form, but is not the causal handle. To separate decodability from causal use, we analyze concentration, alignment, and semantic location. These diagnostics explain why behavior, probing, and intervention can diverge. Multimodal training thus reshapes the geometry of text-only reasoning, not just how visual input is processed.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14942
PDF
-
Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen
2026-11-11 02:35:53Richard J. Young, Alice M. MatthewsAbstract
Racial and ethnic minority patients receive less pain treatment than non-Hispanic White patients, and large language models (LLMs) used as medical AI could reproduce that bias. Prior audits tested a few proprietary models, stated race explicitly and rarely measured the models' own response instability. In exploratory, non-preregistered analyses, Study 1 had four open-weight LLMs assess six acute-pain vignettes in every combination of four races and two sexes, with identity stated or cued only by a name (two names per group), comparing each identity with a White male reference on the same case and sampling seed. In Study 2, 24 configurations of 17 models, including OpenAI's GPT-4.1 mini and gpt-oss, Anthropic's Claude Haiku 4.5, Google's Gemini 2.5 Flash, Meta's Llama, DeepSeek and Qwen, with reasoning on and off and at two precisions, answered the same vignettes and the 50 clinician-written Q-Pain cases. In this single-prompt, JSON-constrained task, no difference survived correction in Study 1, none of 1,386 comparisons survived the false discovery rate in Study 2, and every pain-severity difference was equivalent to zero within one point on a 0-10 scale (within a quarter point for 237 of 238 Q-Pain comparisons). Opioid decisions were bounded less precisely (Study 1 could not exclude differences of about 20 percentage points), so they show no detected difference, not proof of none. The few differences surviving correction within a model favoured Black patients. Models differed far more from one another and across their own settings than between patients (the reference patient received the high opioid dose in 6% to 93% of responses), although serving software, provider and prompt format also differed. Fairness audits of clinical AI should use several names per group, pair comparisons on the seed, report the noise floor and test each deployed configuration.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14935
PDF
-
Edge-Native Multimodal RAG: Hardware-Aware Quantization and Architectural Optimization for Consumer GPUs
2026-11-11 02:26:07Zahraa Selim, Menna Hamed, Wesam Ahmed, Sohyla Said, Sara Basheer, Rami ZewailAbstract
Deployment of retrieval-augmented generation (RAG) for Edge-AI is constrained by memory and bandwidth limitations. A standard 7B parameter model consumes 14 GB Video Random Access Memory (VRAM) in half-precision (FP16), precluding co-location of vector indices and Key-Value (KV) caches. This paper presents an engineering integration and empirical evaluation of a multimodal RAG framework optimized for consumer-grade Turing hardware (e.g., NVIDIA Tesla T4). Our system-level analysis identifies a critical trade-off: while generative pre-trained transformer quantization (GPTQ) offers superior throughput (51.6 tok/s), it exhibits significant context instability at 2048+ tokens on Turing architectures. Conversely, NormalFloat 4-bit (NF4) maintains robust long-context performance with viable latency (81 ms/tok). By coupling NF4 with a decoupled Florence-2 vision integration, we achieve visual reasoning with only 430 MB VRAM overhead. Furthermore, empirical observations of prompt-induced search space pruning show that structured prompting reduces latency by 47% without altering computational intensity (1.88 GFLOPs/token). The integrated architecture maintains an 8.37 GB footprint, establishing a viable RAG pipeline for 12-16 GB GPUs. Finally, structured few-shot prompting effectively compensates for quantization-induced reasoning loss, restoring mathematical accuracy from 35.0% to 92.0% across 200 trials.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14924
PDF
-
Rethinking 'RL Generalizes, SFT Memorizes': The Role of SFT Data
2026-11-11 02:10:24Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li, Zhuoran YangAbstract
Large language models trained with Reinforcement Learning (RL) with verifiable rewards exhibit strong reasoning ability and broad generalization, whereas models trained with Supervised Fine-Tuning (SFT) are often viewed as more prone to memorization and limited transfer. This paper rethinks this distinction through the lens of SFT training data on widely used Qwen2.5 and Qwen3 series models. First, we study the role of data source and show that it is critical: a carefully mixed SFT dataset substantially outperforms data generated solely by a larger model. Second, we study the role of data scale and show that matching the number of correct rollouts between SFT and RL greatly improves SFT generalization, while matching the total rollout budget enables SFT to generalize as well as RL. Combining these two factors further enables SFT to generalize even better than RL. Third, by using LLM annotations to characterize the solution methods in training rollouts, we show that larger datasets cover more tail methods and that these tail methods provide generalizable reasoning signals. Finally, we support these empirical findings theoretically by analyzing the training dynamics of shallow transformers under both RL and SFT.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14912
PDF
-
Learning Low-Latency Action Verification for Frozen Vision-Language-Action Models
2026-11-10 23:32:12Wen-Han Hsieh, Ken Jiankun Zheng, Chia-Chien Chen, David M. Chan, Trevor DarrellAbstract
Vision-language-action (VLA) models have made significant progress in general-purpose robotic manipulation. However, sampled action sequences can be ineffective, while evaluating alternatives with computationally expensive verifiers adds latency at each policy query. In this work, we propose HDH, a lightweight framework that uses hindsight from a frozen VLA's own deployments to improve action verification. The framework has three stages. First, we deploy the policy and collect its autonomous rollouts. We then train a compact action verifier to assign each action chunk a predicted task-success score. Finally, the frozen VLA generates action candidates, and the verifier selects the candidate with the highest score for execution. Across four LIBERO-10 tasks, HDH achieves an average success rate of 82.3\% and on three real-world manipulation tasks, HDH improves average success over the baseline policy by 22.6\%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14834
PDF
-
Robust Task-Aware State Estimation from Pre-trained Perception
2026-11-10 22:12:54Guy Azran, Sarah KerenAbstract
Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into a single best-guess state and make decisions as if it were ground truth. This is brittle because when the guess is wrong, the agent's decisions may be unsafe or infeasible. At the other extreme, maintaining a full probability distribution over symbolic states is often intractable. We propose a middle path, drawing on the underlying probabilities the perception model already produces (e.g., a VLM's output-layer token distributions) to construct a $\theta$-confidence Minimal Belief Set (MBS$_\theta$), a minimal subset of states whose cumulative probability meets a user-specified belief-mass threshold. The minimality of an MBS$_\theta$ ensures that the agent considers only the most likely states, enhancing robustness in downstream decision-making while maintaining computational tractability. Using a novel three-layered belief system, we efficiently approximate individual state probabilities from per-feature predictions and task-level constraints. On this belief construction, we base our MBS$_\theta$ construction, while maintaining only a lean factored representation of the belief. Our algorithm, Probability-Ranked Valid State Search (PRaVaSS), takes advantage of the unique structure of this belief system to construct an MBS$_\theta$ with correctness guarantees and polynomial complexity in the unconstrained case. Using a VLM as the backbone of our state estimator, we validate our method's theoretical properties, scalability with problem size, and improvement of downstream decision-making when used in a task-planning pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14781
PDF
-
Graph Label Alignment: A Diagnostic Atlas for Graph Classification
2026-11-10 21:36:10Neelam Akula, Varun Shiralkar, Murat Kantarcioglu, Baris CoskunuzerAbstract
Graph classification benchmarks vary widely in difficulty: some are solved by simple pooled baselines, while others remain challenging for GNNs and graph transformers. We take a data-centric view and ask whether benchmark success is driven by genuine structure--feature reasoning or by label signal already accessible from restricted marginal views. We introduce graph label alignment, a lightweight diagnostic that measures label accessibility through two supervised probes computed without training a graph encoder: structural label alignment (SLA), based on permutation-invariant topological and spectral summaries, and feature label alignment (FLA), based on pooled node features with edges removed. Across real graph classification benchmarks and multiple pooled backbones, the resulting SLA--FLA plane strongly organizes test accuracy, with low-alignment datasets forming a consistent regime where standard pooled pipelines struggle. To probe what lies beyond marginal accessibility, we introduce controlled interaction-dominated stress tests, including heterophilic ego-graphs and synthetic Twins tasks whose structural and feature marginals are matched across classes but whose role--feature couplings differ. These results show that high alignment explains much of easy benchmark performance, while low alignment reveals regimes where success requires preserving structure--feature correspondence beyond standard pooled representations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14760
PDF
-
Benchmarking Multilingual Document Understanding in Vision-Language Models
2026-11-10 21:35:26Matteo Gabburo, Daniela Baiamonte, Stefano Simonazzi, Silvia Gardini, Sean Cesare Lazzeri, Andrea ZugariniAbstract
Recent Vision-Language Models (VLMs) perform strongly on multimodal tasks, Document Understanding (DU) among them, but the benchmarks that measure them mostly cover English documents and narrow problems. How well current VLMs generalize across languages, tasks, styles and layouts therefore remains unclear. We introduce MDU, a multilingual DU benchmark of 23146 examples spanning 13 tasks and five languages: English, French, German, Italian, and Spanish. The tasks isolate complementary capabilities, from surface-level text and Markdown extraction through summarization, classification and named-entity recognition to layout-sensitive passage and layout extraction. We evaluate 45 state-of-the-art open-weight VLMs from 1.7B to 235B parameters, plus one commercial system under the same protocol. The benchmark is far from saturated: the best average is 69.0, only eight of the 45 evaluated systems reach 65, and the two best results come from 27B models rather than from the largest systems we evaluate. Performance is uneven in ways that scale does not fix. The gap between the strongest and weakest language does not close as models grow, and it survives controlling for the domain composition of each language. Capabilities also do not improve together: once we partial out overall model quality, per-task scores are largely uncorrelated, and transcription ability in particular trades off against semantic extraction.
Abstract (translated)
URL
https://arxiv.org/abs/2611.14758
PDF
