NeurIPS 2026 Papers

Theory of Mind (ToM), the ability to infer others’ knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by requiring explicit modeling of belief structures for all relevant actors within a narrative. These structures are composed of belief propositions: minimal statements of what an actor takes to be true about the world or another actor's mental state, allowing knowledge, intentions, emotions, and false beliefs to be analyzed in a common format. Models are evaluated in two stages: Stage 1: Belief Extraction, which extracts from the story the beliefs relevant to its social dynamics, and Stage 2: Belief Labeling, which assigns each belief a seven-dimensional schema label covering recursive order, truth status, knowledge access, explicitness, content type, mental source, and context. Built from 895 stories from the existing ToMBench story corpus and augmented with 22,343 labeled belief propositions, OmniToM uses a human-calibrated LLM-assisted annotation pipeline. Across diverse models in zero-shot evaluation, OmniToM reveals an actor-specific belief-tracking bottleneck: current LLMs struggle with the knowledge-access and representational decisions required to transform narrative facts into actors’ beliefs and shared mental states.

Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Autonomous Vehicles (AV) remains an open challenge. Existing geometry-aware MLLMs typically rely on auxiliary 3D models at inference time, introducing pipeline complexity and the risk of cascading failures. In this paper, we present OmniSpace, a simple yet effective plug-and-play paradigm for geometry-aware spatial reasoning from purely 2D observations. Motivated by our finding that current MLLMs are bottlenecked by weak cross-view correspondence and depth estimation, OmniSpace introduces a Camera Pose Injector, a Multi-view Epipolar Attention module, and a 3D Geometric Distillation objective that jointly address these two limitations by transferring geometric knowledge into the model. Extensive experiments show that OmniSpace surpasses existing methods on planning benchmarks (nuScenes, Bench2Drive), risk detection (nuInstruct), language (Omnidrive), and generalization (DriveBench).

Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reasoning and downstream task performance. However, the upper bound of user simulation is still constrained by the model's reasoning paradigm: standard chain-of-thought often degenerates into shallow pattern matching and fails to capture the latent mental process underlying real user behavior. In this paper, we propose OmniSimulator, a novel training framework designed to improve the predictive ability of small LLMs for realistic user simulation on short-video platform environments. Specifically, OmniSimulator models human internal deliberation through a structured reasoning schema with five dimensions, carefully selects data from real user-behavior scenarios, and introduces a teacher model to generate high-quality reasoning traces under the proposed schema, boosting small models to learn the latent logic of human decision-making during the CoT process, rather than relying on superficial behavioral correlations. Based on this process, we construct 9,881 high-quality training instances from three months of historical interaction trajectories of 200 real users, averaging about 50 distilled examples per user. Experimental results show that OmniSimulator improves performance over the baseline by 38.93\%, surpasses strong frontier models such as Claude-Sonnet-4.5, and significantly reduces inference cost. These results suggest that learning structured human-like internal reasoning is a key step toward scalable and high-fidelity LLM-based user simulation.

Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long multimodal token sequences introduces substantial computational overhead, making efficient token compression crucial. Existing methods typically rely on fixed, modality-specific guidance, which fails to account for the varying importance of modalities across different queries. To address this limitation, we propose $\textbf{OmniSelect}$, a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs. Specifically, we leverage a lightweight AudioCLIP model to estimate cross-modal relevance and categorize each input into three pruning regimes: Audio-Centric, Video-Centric, and Uniform pruning. Based on these relevance scores, OmniSelect further performs fine-grained token pruning within each temporal group, adaptively allocating pruning ratios to preserve informative tokens across modalities. By explicitly modeling modality preference and enabling dynamic strategy selection, OmniSelect effectively avoids the pitfalls of one-size-fits-all compression. Extensive experiments demonstrate that our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.

Omni-modal models are expected to reason over synchronized visual events and audio cues, yet answer accuracy alone can conceal failures in where an answer is grounded and which modality supports it. In audio-video question answering (AVQA), models may produce correct answers while relying on incorrect temporal spans, dominant-modality shortcuts, or unsupported cross-modal relations. We argue that this failure arises from treating reasoning as a completion-level prediction problem, where supervision and reward signals do not distinguish between support selection and reasoning over the support. To address this, we introduce OmniSE, a support-faithful optimization framework that makes question-conditioned audio-video support the central training object. Each QA instance is rewritten into an Audio-Visual Evidence Trace, a compact optimization unit that records temporal evidence, modality-specific cues, cross-modal relations, and cited reasoning steps. Given this support object, OmniSE first uses Support-Tree Rollout (STR) to explore alternative support hypotheses before sampling support-conditioned reasoning and answers. It then applies factorized reward assignment to score temporal localization, modality evidence, cross-modal binding, reasoning faithfulness, and answer correctness at their corresponding comparison levels. Finally, reward-gated self-consistency regularizes sibling continuations under reliable support, encouraging fixed trustworthy evidence to induce stable reasoning and answers. Experiments on multiple AVQA benchmarks show that OmniSE consistently outperforms strong open-source baselines at the same scale, demonstrating the importance of support-centric optimization for evidence-centric audio-video reasoning. Code and data would be publicly available after peer review.

Multimodal agents that interact with users over days or months must remember not only what was said, but what was shown, heard, and played. Current memory benchmarks are predominantly text-only or cover at most two modalities. Those that do incorporate multimodal content still evaluate with aggregate scores that conflate retrieval and reasoning errors, and provide no mechanism to test whether performance degrades as context scales, leaving our understanding of agent memory fundamentally incomplete. We introduce OmniMemBench, to our knowledge the first long-term memory benchmark that spans image, audio, and video in multi-session dialogue. Its design is guided by three requirements for reliable evaluation. First, an anti-leakage mechanism filters questions answerable from text alone, reducing text-only solvability to a negligible level. Second, two LLM-judged retrieval metrics—Clue Coverage and Entry Relevance—operate on content rather than entry IDs, enabling unified retrieval diagnosis across RAG and memory paradigms. The gap between retrieval coverage and downstream QA scores further localizes failures to the memorization stage. Third, content-isolated distractor injection scales context from 128K to 1M tokens while holding evidence constant, so scalability can be measured without confounding difficulty. The benchmark covers 103 characters and 6,655 QAs across 8 task types and 4 context tiers. Evaluating representative long-context, RAG, and structured-memory methods, we find that no single paradigm dominates: long-context models lead overall, yet RAG surpasses them on targeted fact extraction. Further analysis shows that memory methods retrieve clues at coverage rates comparable to RAG but score substantially lower on QA, revealing that the bottleneck is not what is retrieved but what is lost during memorization. Caption-based processing irreversibly discards perceptual details; raw embeddings degrade retrieval accuracy; and scaling the memorization model yields negligible gains.

Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. Existing methods reduce this cost by truncating the KV cache or compressing it into implicit memory, but both lose explicit access to query-relevant historical details. We propose OmniMem, an explicit full-range memory retrieval framework that performs sparse KV retrieval over the historical cache. To make this practical for chunk-based AR video generation, OmniMem addresses two issues: (i) local bias in sparse KV selection and (ii) Union Explosion in memory access. Adaptive Window Exclusion removes local-window blocks from the selection candidates when sufficient long-range history is available, preserving the sparse budget for informative long-range retrieval. Query-shared KV Selection reduces cross-query diversity, while Per-Head Scattered KV Access avoids expanding head-specific selections into a large selected KV buffer. This allows each attention head to retrieve non-contiguous KV blocks according to its own selection pattern. Experiments on long-video generation show that OmniMem improves Dynamic Degree by 52.3\% and preserves strong consistency over strong baselines, while maintaining comparable memory usage.

As AI systems are increasingly deployed in high-stakes domains such as healthcare, effectively integrating human expertise with AI outputs is critical for reliable decision-making. A substantial body of theoretical work studies optimal mechanisms for human-AI collaboration (HAC), focusing on when to involve humans and how to combine their expertise with AI predictions. However, these approaches largely overlook a key factor highlighted by empirical evidence: human judgments are impressionable and can vary depending on how AI outputs are presented. For example, when AI systems defer decisions to humans, revealing or withholding the AI prediction can significantly influence human judgments. Moreover, existing work neglects deployment-time variability, where conditions, particularly the cost of eliciting human input, may differ substantially from those observed during training. To address these challenges, we introduce a rigorous and theoretically grounded framework for human-AI collaboration, termed \emph{collaborative omnimechanism design}, based on a novel and computationally efficient contextual bandit variant of boosting for outcome indistinguishability. In particular, we reduce a calibration-type outcome indistinguishability condition to projected smooth calibration, providing novel time-efficiency result, bypassing the high-dimension curse induced by complicated collaboration methods. Our framework provides a principled characterization of human impressionability and introduces a unified optimization scheme that enables robust and adaptable decision-making across diverse query costs and evaluation objectives without retraining. We further validate our theoretical results through comprehensive experiments.

Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure spatial localization, lacking the high-level capacity to reason about semantic targets or complex social contexts. Furthermore, these models often process individuals sequentially, requiring redundant computations over the same scene image for multi-person inference. While recent Vision-Language Models (VLMs) offer the exceptional semantic reasoning needed to address gaze-related semantic tasks, their reliance on discrete text generation inherently limits precision in continuous spatial tasks like gaze localization. To bridge this gap, we propose OmniGF, a unified vision-language framework that adapts foundational VLMs for highly scalable multi-person gaze reasoning. The model adopts a dual-branch decoding strategy: a structured language branch generates discrete reasoning states, while a continuous spatial branch directly taps into the VLM's dense hidden states. Supervising these extracted representations with high-resolution gaze target heatmaps effectively overcomes the spatial bottleneck of text-only coordinate generation. Furthermore, to explicitly ground the model in multi-person scenes, we augment the input with head embeddings encoded from cropped head images, providing fine-grained appearance and orientation cues for all individuals simultaneously. By modeling all individuals and leveraging the strong semantic capability of VLMs, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning. Extensive experiments demonstrate that our framework establishes new state-of-the-art performance across multiple standard benchmarks.

Commercial egocentric devices capture human behavior in everyday settings, yet full-body motion reconstruction must generalize across diverse cameras and mountings. This is challenging because head trajectories under-determine body motion, while hand observations are intermittent and camera-dependent: a hand may disappear simply because it has left the camera's field of view. Existing methods treat such absences as missing data, relying on fixed visibility regimes or post-hoc optimization, and fail to generalize across devices.We present \modelname, a sequence-level diffusion framework for device-agnostic egocentric full-body motion reconstruction. Our key insight is that egocentric videos contain sequence-level evidence about both the wearer and the camera-induced visibility structure, enabling \modelname to infer consistent body shape and coherent motion from sparse head and hand cues. To prevent overfitting to a single camera setup, we further introduce geometry-aware visibility augmentation, which synthesizes visibility patterns from realistic variations in camera geometry. We also present OmniEgoDB, the first mocap benchmark with ground-truth motion captured across multiple consumer egocentric devices. Experiments on synthetic, real-device, and in-the-wild settings demonstrate superior motion reconstruction, robust cross-device generalization, and coherent in-the-wild results.

Dexterous grasping is the foundational primitive in embodied AI, demanding massive data to train robust models. As real-world data collection is expensive, simulation has become the mainstream paradigm. Yet, while cluttered scenes best reflect real-world applications, learning to grasp within them is bottlenecked by a critical scarcity of large-scale data. To resolve this, we curate high-quality 3D objects and supporting bases, proposing a scalable seed-and-filter strategy that bypasses sluggish scene-level optimization. This yields an unprecedented benchmark comprising over 2.6 million scenes and 0.4B scene-specific grasp ground truths, featuring diverse realistic layouts paired with rich semantic and geometric observations. Furthermore, we introduce the OmniDex model to overcome the grasp multimodality and last-millimeter precision errors plaguing current generative models. By coupling Soft Winner-Takes-All learning with human-inspired physical constraints during training, and utilizing physics-driven ranking, our approach achieves robust dexterous grasping without the latency of post-optimization. Experimental results show that OmniDex model achieves state-of-the-art performance and strong generalization across diverse scenes, views, and unseen objects.

Omni-modal Large Language Models (OLLMs) greatly expand LLMs' multimodal capabilities but also introduce cross-modal safety risks. However, a systematic understanding of vulnerabilities in omni-modal interactions remains lacking. To bridge this gap, we establish a modality-semantics decoupling principle and construct the AdvBench-Omni dataset, which reveals a significant vulnerability in OLLMs. Mechanistic analysis uncovers a Mid-layer Dissolution phenomenon driven by refusal vector magnitude shrinkage, alongside the existence of a modal-invariant pure refusal direction. Inspired by these insights, we extract a golden refusal vector using Singular Value Decomposition and propose OmniSteer, which utilizes lightweight adapters to modulate intervention intensity adaptively. Extensive experiments show that our method not only increases the Refusal Success Rate against harmful inputs from 69.9% to 91.2%, but also effectively preserves the general capabilities across all modalities.

Multimodal representation learning has been shifting from traditional two-tower architectures to large language model (LLM)-based embedders due to their strong instruction-following capabilities. Despite this progress, existing approaches primarily focus on language and image modalities, which also remain the dominant modalities for human-AI interaction in current embedders. In this paper, we propose the first Omni-Interactive Universal Embedder (OmniUE), which not only learns a unified embedding space across text, video, and audio by leveraging intermediate-layer representations from dedicated learnable tokens, but also supports omni-interactive querying, enabling users to provide inputs in the form of text, visual regions of interest, and audio spans. Within OmniUE, visual and audio segmenters process diverse user interactions and integrate them with an omni-LLM to produce user-conditioned any-to-any embeddings via context aggregation. To evaluate OmniUE’s omni-interactive capabilities, we introduce OmniCHOIR, benchmarking models for omni-interactive compositional audio retrieval based on the given text, video, and audio as well as unimodal or multimodal interaction prompts. OmniUE consistently surpasses state-of-the-art baselines across diverse modalities, with average improvements of 10.5% on textual-interactive video benchmarks (MMEB-v2-video), 1.1% on audio tasks (MAEB), 83.7% on visual-interactive benchmarks (SCaR), and 24.1% on our omni-interactive OmniCHOIR benchmark We believe that jointly advancing omni-modal representation learning and omni-interactive querying paves the way toward universal embedders.

Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime $n \gg p$, where the number of graphs $n$ greatly exceeds the number of nodes per graph $p$. This overlooks biological domains such as omics, which operate in the opposite $n \ll p$ regime, characterized by large graphs of genes, transcripts, or proteins across few patient samples. This raises the question: \textit{how do GNNs perform in this low-sample, high-node omics setting?} We introduce \texttt{OgBench} (Omics-Graph Bench), the first benchmarking platform for graph-level prediction in the $n \ll p$ regime characteristic of omics data. We provide a standardized, end-to-end modular infrastructure from raw omics data to families of featured graphs with varied structural properties. We benchmark classical GNNs, as well as GNNs designed for large graphs and omics applications, alongside MLPs and machine learning baselines to establish reference performances. Our results show that widely used GNNs often do not outperform simple MLPs and classical baselines. These findings challenge the prevailing assumption that graph structure inherently adds value in this domain, fostering a critical reassessment of current learning paradigms. Ultimately, by exposing these limitations, OgBench provides the open-source ecosystem necessary for the community to develop and validate novel architectures explicitly tailored for biological graphs. The code is available at \url{https://anonymous.4open.science/r/ogbench-C1A9/README.md}.

AI tools are increasingly integrated into real-world workflows. However, existing measures of reliance on these tools focus on AI output adoption or on self-reported indicators, rather than how task effort is distributed between users and tools. Here, we introduce offloading score, a measure of reliance that quantifies the fraction of cognitive effort offloaded to an AI tool. Offloading score is simulation-based---we construct a counterfactual workflow by estimating how the user would have completed the task without the tool, and then computing the fraction of steps saved by using the tool. We validate offloading score through intrinsic evaluations of metric validity, and a controlled user study ($n=40$) with developers performing programming tasks using AI tools. We vary time pressure to test whether reliance measures capture the known increase in reliance under time pressure. We show that offloading score detects significantly higher reliance in time-constrained settings ($+43\%$, $p=0.018$), while usage-based and self-reported baseline measures do not distinguish the conditions. We complement this with descriptive insights showing that higher reliance manifests as greater delegation and more direct reuse of AI outputs. Finally, we demonstrate an approach of using offloading score in combination with target outcomes of reliance (e.g., task understanding) to identify when reliance may be (in)appropriate. Our framework offers two contributions: an instrument users can apply to measure and reflect on their own reliance, and a quantitative signal that agent designers can utilize to mitigate overreliance.

Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky. However, progress in this direction remains difficult to measure due to the lack of a standardized offline RL benchmark for realistic multi-actuator, long-horizon plasma control problems in nuclear fusion. We introduce RL4F, an Offline Reinforcement Learning Benchmark for Plasma Control in Nuclear Fusion, providing closed-loop evaluation environments and baseline comparisons across four full-profile tracking tasks: rotation, density, temperature, and pressure. The dynamics function underlying the evaluation environment is built from historical discharge data from DIII-D, a real-world Tokamak. We evaluate a broad set of imitation learning and offline RL baselines under a unified protocol. We find that offline model-based RL methods obtain the best average performance on most objectives, although no single method dominates all tasks, highlighting the importance of dynamics modeling in complex, long-horizon plasma control tasks. To foster further research, we open-source the codebase, datasets, and evaluation framework, providing a benchmark not only for the fusion community but also for algorithm development in offline RL. Our data and code are available at https://anonymous.4open.science/r/Anonymous-B71F

Offline evaluation of agentic systems often collapses trajectories to terminal success, discarding information about partial progress and inducing widespread ties. We argue that this trajectory collapse creates substantial statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems. We propose preference-based trajectory evaluation, which compares trajectories directly through temporal preferences over progress and time-to-return profiles. Across diverse agentic and interactive benchmarks, standard success-based metrics produce tied comparisons on roughly 75\% of instances, whereas trajectory-aware preferences reduce ties to roughly 30\%, improving discriminative power, ranking stability, and data efficiency. Our results suggest that benchmark saturation, often portrayed as the result of poor data collection or problem difficulty, may also be explained by the choice of evaluation measure.

Recent advances in deep learning have inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling methods are ineffective at boldly exploring attractive regions of the materials space due to their maximum likelihood training. In this work, we offer an alternative CMD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. To that end, we introduce a domain-specific model, CliqueFlowmer, that incorporates recent advances in clique-based MBO into transformer and flow generation. We validate this model's optimization abilities and show that materials it produces strongly outperform those from generative baselines. To support specialized materials discovery applications and broader interdisciplinary research, we will release our code and model weights upon publication.

Offline Inverse Reinforcement Learning (IRL) aims to recover a reward function and imitate expert behavior solely from offline demonstrations. While recent Offline IRL approaches employ approximate dynamics to mitigate distribution shift, their performance is constrained by the unstable minimax framework as well as simplified representation and utilization. To address these issues, we propose Offline Inverse Reinforcement Learning with Diffusion Planner (OIDP), which leverages diffusion models to achieve stable Offline IRL. OIDP formulates a model-based conservative Q-optimization through inverse soft Q-learning, which is provably concave in Q-space with a controllable performance gap. Accordingly, we introduce a unified diffusion planner that models dynamics, uncertainty estimator, and policy, it captures multimodal distributions, directly tightens the objective gap bound, and at execution performs trajectory-guided policy sampling using the internalized dynamics knowledge. Experimental results on D4RL benchmarks demonstrate that OIDP outperforms state-of-the-art offline approaches.