NeurIPS 2026 Papers

Multimodal language models increasingly show promise for enabling the large-scale computational analysis of film, opening up new avenues for learning about film history and the evolution of narrative techniques. But the creation of stable benchmarks built around Hollywood films is complicated by copyright protections. In this work, we address these concerns directly, by building a new collection of Hollywood films defined by two criteria: box office popularity (where we publish the first large-scale, open collection of weekly box office earnings reported by Variety magazine from 1922-1979); and likely public domain status (by researching copyright registrations and renewals in the US Catalog of Copyright Entries). We build a new multimodal MCQ benchmark on top of this collection that focuses on narrative elements that directly evaluate the abilities of models to inform meaningful research on film narrative; we find that many vision-language models struggle on this task (with many performing at near-chance levels of accuracy), while audio-visual models (including those that use audio in captioning scenes) reach a maximum accuracy of 61.1%, well below human-level performance.

The goal of asymmetric pansharpening is to synthesize a high-resolution multispectral (HR-MS) image by integrating panchromatic (PAN) and low-resolution multispectral (LR-MS) images. While State Space Models (SSMs), particularly Mamba, offer a promising paradigm for global dependency modeling, their standard selective scan mechanisms operate in discrete Cartesian grids, which are ill-suited for distinguishing between structural and spectral features in complex-valued frequency representations. To resolve this, we propose Euler-Mamba, a physics-inspired framework that reformulates the selective scan as a continuous state evolution on polar manifolds. We develop an Eulerian Selective Scan (ESS) mechanism that treats the fusion task as a trajectory of frequency growth. By performing radial scans within the polar domain, ESS governs complex-valued state transitions through the decoupled architecture: the Explicit Phase Rotation (EPR) block facilitates explicit phase rotations for geometric alignment, while the Implicit Magnitude Mapping (IMM) block performs magnitude scaling for spectral calibration. This polar-decoupled evolution allows the model to capture the continuous transition from global spectral backgrounds to fine structural details with linear complexity. Consequently, by modeling the fusion as a continuous functional evolution flow, Euler-Mamba achieves resolution-invariant performance and zero-shot generalization across varying spatial scales, bypassing the computational complexity inherent in traditional discrete-integration frameworks. Extensive experiments demonstrate that Euler-Mamba establishes a new Pareto frontier for asymmetric pansharpening, achieving a superior balance between physical interpretability, computational efficiency, and reconstruction quality.

Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgetting, particularly the performance degradation of previous tasks and LLMs' general-purpose knowledge. Although existing methods, such as orthogonal gradient projection, mitigate the forgetting across various fine-tuning tasks, they fundamentally fail to preserve pre-training LLMs' inherent general-purpose knowledge because the original data and gradients of off-the-shelf pre-training LLMs required by these methods are strictly unknown and highly diverse. To bridge this critical gap, we propose EoupCT, a novel framework designed to Estimate and Orthogonalize Unknown Pre-training gradients for Continual LLM fine-Tuning. Specifically, EoupCT estimates pre-training gradients by dynamically generating pseudo data that is most susceptible to forgetting for new tasks through a learnable soft prompt equipped with Gumbel-Softmax relaxation. Furthermore, we formulate a multi-objective optimization problem and introduce a first-order efficient Pareto optimizer that jointly optimizes LLM parameters and the soft prompt, rigorously enforcing orthogonality between new task updates and the estimated pre-training gradients. Extensive experiments across multiple LLMs demonstrate that EoupCT effectively preserves both task-specific proficiency and inherent general-purpose knowledge, successfully mitigating the catastrophic forgetting.

Inference-time search (e.g., Tree of Thoughts, ToT) with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternatives underexplored—a failure mode we call \textit{reasoning basin collapse}. We introduce \textsc{BASIN}, a training-free selection method that penalizes repeated visits to the same reasoning basin, defined symbolically for arithmetic tasks or semantically via hypothesis clustering, thereby reallocating search across diverse reasoning strategies. Under matched inference budgets, \textsc{BASIN} improves over ToT by up to $+22$pp on Game of 24. To explain why this quality-agnostic penalty is effective, we introduce the \emph{redundancy gap} $\Delta$, which measures how differently search concentrates for correct versus incorrect predictions: standard ToT often operates near $\Delta \approx 0$, failing to distinguish correct from incorrect searches by their visit patterns, while \textsc{BASIN} consistently induces $\Delta > 0$, concentrating search on correct basins while dispersing incorrect ones. More broadly, \textsc{BASIN} suggests structure-aware selection as a simple and general approach to improving inference-time reasoning.

Video understanding is commonly built on action-triggered responses or scene-level aggregation, implicitly assuming clear temporal boundaries. This assumption breaks in dense-action streams such as gameplay and sports, where overlapping actions induce continuous latent dynamics without explicit transitions. The challenge is further amplified in streaming settings, where models operate under strict causal constraints and must progressively construct episodic memory for downstream reasoning. Existing segmentation-based strategies therefore often produce fragmented or semantically mixed episodes, leading to degraded understanding. We present EpiStream, an online framework for utility-aware semantic episode formation in dense-action streams. Instead of detecting event boundaries, EpiStream learns when an evolving video prefix should be committed into an episode unit that maximizes downstream utility under limited memory budgets. The framework consists of three steps: (i) utility function design for semantic coherence, inter-episode distinctiveness, and downstream objectives; (ii) utility-optimal commit advantage construction from teaching signals; and (iii) peak-aware advantage learning for training a causal online commitment policy from prefix-only observations. Extensive experiments show that EpiStream substantially improves temporal semantic coherence and consistently benefits challenging downstream tasks, including real-time advice and player intention prediction.

As AI models evolve from text and vision to physical agents, embodied AI faces a fundamentally different attack surface. Prior attacks on embodied systems have largely focused on semantic or instruction-level manipulations, such as prompts, adversarial images, and action commands; by contrast, we study environment-only perturbations that require no access to the model or instructions. We reveal a new attack surface: the physical environment itself. An adversary who rearranges objects, without modifying instructions or accessing models, can cause hazardous consequences. In this work, we propose EnvTrap, a diagnostic pipeline that constructs paired safe, trap, and null-trap (benign but misleading) embodied scenarios. We demonstrate that environment-only perturbations raise hazardous-action rates to an average of 86.5\% across multiple vision-language-action (VLA) models, with similar vulnerability patterns confirmed in world models. On a consequence-prediction task, model accuracy remains near chance, while human evaluators succeed easily. We further propose a consequence-aware defense that reduces trap trigger rates by an average of 76.3\% across VLA models in simulation and by 61.7\% on physical robots. This vulnerability arises because current embodied models can recognize scene state but often fail to predict action consequences under altered layouts. Our findings establish environment integrity as a prerequisite for safe embodied AI deployment. Our code and data are available at https://anonymous.4open.science/r/Envtrap-1BA4/

Large language models are increasingly used to simulate human participants in social and behavioral studies, yet static persona prompting typically maps a participant profile and an experimental scenario directly to a response, entangling stable dispositions with situation-specific interpretations. To address this limitation, we introduce $\textbf{SPIN}$, a cognitive-affective personality system-inspired inference pipeline for social judgment and decision alignment. Specifically, SPIN implements this structured inference process through three zero-shot LLM calls that compile a task-blind participant core, elicit condition-specific cognitive-affective states, and read out decisions from those states, thereby reusing stable personality structure while routing each trial-specific response through an explicit state representation. We evaluate SPIN on two reconstructed social-psychological study families spanning uncertainty reasoning and pluralistic ignorance, across four base LLMs. Compared with blank, demographic, narrative, and chain-of-thought prompt variants, SPIN consistently delivers the strongest overall alignment performance across base LLMs and study families. Ablations and state analyses further show that both personality compilation and structured state elicitation contribute to the gains, and that the elicited states shift interpretably across informational and normative conditions. These results suggest that structured personality-state inference can improve benchmark-level behavioral alignment beyond richer persona descriptions or generic multi-step reasoning.

Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning. As a result, existing methods often rely on semantically salient objects rather than true gaze cues, leading to degraded performance when targets are not salient. To address this, we propose a novel training mechanism to enhance gaze reasoning in VFMs for gaze following. Our method includes: (1) a head-conditioned local LoRA, which enables localized adaptation to preserve scene token learning while improving head token learning for gaze reasoning; and (2) an out-of-cone penalty, which injects gaze cues into head tokens while aligning them with scene tokens. Experiments on the GazeFollow and VAT datasets demonstrate that our method achieves state-of-the-art performance, with particularly strong improvements when gaze targets are not semantically salient. Our findings offer valuable insights for advancing future gaze following research. We will release the code once the paper is accepted.

Real-world endoscopic diagnosis unfolds across native video, depending on continuous traversal of gastrointestinal organs where a single positive finding triggers a multi-minute reasoning chain over location, morphology, severity, and intervention. Existing endoscopy multimodal benchmarks evaluate only static images or single-disease videos that fail to capture the temporal and clinical reasoning demands of real-world endoscopy reporting. We introduce EndoSCOP-V, a video-grounded multi-turn evaluation framework for long-horizon clinical reasoning in endoscopy. The benchmark contains 1,307 real-world endoscopy and colonoscopy videos (63.2 h; 97% 1080p; mean ~174 s) — the time-scale at which endoscopists actually reason about a finding. The corpus is paired with 20,275 question–answer turns deterministically instantiated from clinician-filled structured endoscopy-reporting EHRs, avoiding synthetic or LLM-rephrased per-case annotations. Questions are derived from 1,033 clinician-reviewed templates spanning a clinically aligned 9-task × 30-sub-task reporting taxonomy across 54 World Endoscopy Organization (WEO) MST 3.0 diseases at ~18 templates per disease, substantially deeper per-disease examination than prior endoscopy benchmarks. To mirror real-world case mix, 22% of procedures carry co-existing pathologies, up to six per case. To model the hierarchical and conditional nature of clinical reporting, EndoSCOP-V introduces a Markovian context-pruned oracle-forcing protocol that evaluates multi-turn dialogues turn-by-turn. By injecting the gold answer before each subsequent turn, the protocol isolates per-turn reasoning from cascading dialogue errors and enables fine-grained analysis of clinical reasoning capabilities. Clinician-marked key-frame anchors further separate temporal-localization from frame-level comprehension failures. A panel of 15 board-certified endoscopists anchors a 78% strict-accuracy baseline on a 1,500-question audit. Across 14 open-weight LMMs, the best 27B-class model reaches 59.8% strict accuracy, falling to 53.4% once format-trivial disease-rejection items are excluded. On a between-subjects spot-check, the best of 3 frontier proprietary models trails the clinician panel by 23 pp on strict accuracy. Sub-task analysis reveals consistent gaps in quantitative measurement, multi-variable grading, and intervention reasoning on long-horizon video, providing a clinically grounded benchmark for evaluating multimodal reasoning in endoscopy.

Test-time sampling can improve Vision-Language-Action (VLA) policies, but only if the model can efficiently select a good action from multiple candidates. Prior work often relies on separately trained external verifiers, adding extra models and inference overhead. We propose \textbf{Token Probability Bucketing (TokenPB)}, a self-verification approach that discretizes continuous action chunks into bucket tokens and co-trains a single VLA checkpoint with a joint objective: a flow-matching loss for action generation and an auxiliary bucket loss $\mathcal{L}_{\text{bucket}}$ that teaches the VLM backbone to model observation-conditioned distributions over bucket-token sequences. At inference, TokenPB samples $M$ candidates, scores each via teacher-forced evaluation under the learned distribution, and selects the best---enabling efficient batched scoring with observation-prefix KV-cache reuse. We provide theory connecting the training objective to a monotonic ranking property and bounds on expected selection regret that separate candidate-set effects from calibration. Across multiple backbones and benchmarks, TokenPB yields consistent success-rate improvements over single-sample inference from the same checkpoint (+2.7 in simulation, +17.1 in real-world, +16.4 under out-of-distribution shifts), and further improves over external-verifier baselines under the same sampling budget.

While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building multimodal foundation models is a natural next step, but it faces key challenges: 1) lack of a unified multimodal pretraining paradigm and large-scale multimodal corpora for time series analysis; 2) how to effectively integrate heterogeneous modalities and enhance model generalization. To address these challenges, we take an early step toward multimodal foundation models for time series analysis. We first propose a multimodal pretraining paradigm that leverages time series with endogenous modalities (derived images and text) and exogenous knowledge (news), providing a comprehensive multi-view perspective for time series analysis. To support this, we develop an automated data construction pipeline to curate MM-TS, the first large-scale multimodal time series dataset spanning six domains, with up to one billion points. Then we propose HORAI, a frequency-enhanced multimodal foundation model. It integrates two core components: the Frequency-enhanced Cross-Modality Encoder and the Time-Frequency Decoder, designed to effectively fuse multimodal features and enhance model generalization across modalities and domains. After pretraining on MM-TS, HORAI achieves state-of-the-art zero-shot performance on time series forecasting and anomaly detection tasks, demonstrating strong generalization.

When large language models (LLMs) are used for creative tasks where the evaluation is largely subjective, two crucial activities are ideation (in which a list of candidate ideas is produced) and pruning (in which the initial candidates are prioritized through a process of comparison). In this framework, the subjective results are influenced by inherent biases in the LLM's generation and evaluation, and it is therefore important to understand how these subjective biases operate. We define and explore a set of stylized tasks that allow us to highlight the effects of these subjective biases in LLM evaluation. In the process, we find evidence for several key underlying principles. First, there are multiple subjective LLM biases at play, and to understand the overall evaluation we must analyze the relative strengths of these biases and their interactions. Second, different prompts -- even when they seem superficially similar -- can have the effect of making different subjective LLM biases more or less salient. And third, there are complex interactions between the LLM's initial idea-generation phase and the subsequent decisions that go into prioritizing and pruning these ideas.

Foundation models trained on large unlabeled corpora develop emergent capabilities — tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-ligand sequences. From a single self-supervised objective, Bonbon exhibits four zero-shot emergent capabilities at hierarchical levels of resolution — functional (mechanism of action), residue (binding site localization, including orthosteric/allosteric discrimination), bond (covalent versus non-covalent engagement), and atom (active moiety identification at single-bond resolution). All four capabilities generalize to out-of-distribution proteins. Bonbon was trained on protein-ligand sequences alone, without any task-specific supervision and without structural coordinates. We conducted controlled scaling experiments across four model scales from 42M to 1.6B parameters; every capability evaluated shows a sharp jump at the largest scale on continuous metrics, even as pretraining loss decreases smoothly. This demonstrates that loss-based scaling laws alone are insufficient to predict when zero-shot emergent capabilities become available. The capabilities reported here emerge after training at a 1:2,000 parameter-to-token ratio to accommodate the sparsity of paired biological interaction data. The same frozen representations achieve state-of-the-art binding and affinity predictions at five orders of magnitude greater speed than structure-based methods. In prospective wet-lab validation, Bonbon achieves a 70% hit rate on de novo compounds, discovering novel chemotypes not previously documented as inhibitors for those targets. All of the tested compounds had less than 60% structural similarity to molecules in the training corpus.

Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increase predicted demand, implied willingness-to-pay estimates are frequently negative or implausible, and unavailable alternatives receive nonzero probability. We propose a two-stage adapter that takes a foundation model's predicted choice probabilities as a precomputed feature and embeds them inside a multinomial logit's utility. In Stage 1, we fit the multinomial logit's structural coefficients by maximum likelihood with sign constraints; in Stage 2, we freeze those coefficients and fit a small neural correction operating on the foundation model's predictions. We prove that this composition exactly preserves the multinomial logit's marginal rate of substitution, so analytically computable value-of-time becomes a mathematical guarantee rather than an empirical accident. Across three datasets and two foundation models, the adapter gains 6.4 percentage points (pp) of test accuracy on average over the multinomial logit and up to 12.8 pp, maintains 100\% cost monotonicity, and produces values of time within the published transportation-economics range on the transportation datasets. Performance degrades gracefully under foundation-model context restriction, retaining at least 6 pp of accuracy gain even at 10\% of the original foundation-model context.

Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point—the standard recipe of encoding each frame into visual tokens yields sequences that grow linearly with video length, causing prohibitive memory consumption and inference latency. Existing approaches, such as token reduction and keyframe selection, attempt to shorten the token sequence but leave the $O(n)$ scaling intact, failing to resolve the fundamental bottleneck. We propose \model, \emph{a strikingly simple, training-free frame packing framework that compresses arbitrarily long videos into a fixed-size visual representation at constant memory cost.} \model requires no fine-tuning, no architectural modification, and no auxiliary models—it plugs directly into off-the-shelf VLMs at inference time, yet consistently surpasses more elaborate baselines. Drawing inspiration from FramePack in generation literature, we propose a new content-aware compression strategy that operates under a fixed token budget for visual understanding. Specifically, \model proceeds in two steps: (1) scoring each frame by its semantic similarity to the text prompt and ranking frames in a diversity-driven manner, and (2) packing the selected frames at varying resolutions into a fixed-length context window. This design concentrates the memory budget on frames that are both instruction-relevant and visually diverse. While in theory \model can pack arbitrarily many frames into the fixed budget, we identify an empirical instantiation that generalizes robustly across different settings. Extensive experiments on LongVideoBench, MLVU, and Video-MME show that \model consistently outperforms full-resolution baselines as well as prior token reduction and keyframe selection methods, across diverse model families, parameter scales, and frame budgets. Notably, on Qwen3.5-35B-A3B with a 128-frame budget, \model yields gains of \textbf{+12.9\%, +10.6\%, and +9.7\%} over the official model on the three benchmarks, respectively.

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for generalist robotic control. However, their high computational cost and limited control frequency hinder real-time robotic manipulation, especially when large vision-language backbones and iterative action heads are executed at every control step. Existing VLA acceleration methods often optimize individual components or rely on fixed acceleration rules, treating different control steps with largely fixed computation and overlooking the non-uniform reasoning demands of sequential embodied control. Inspired by human motor control, where cognitive and feedback resources concentrate on goal-sensitive stages, we argue that VLA models should learn when to invest full computation and when to reuse prior computation. To this end, we propose ElegantVLA, a plug-in phase-adaptive inference framework that accelerates VLA models through intra-model dynamic compute scheduling. ElegantVLA introduces a lightweight scheduler that observes temporal representation similarity, robot-motion cues, and episode progress to jointly allocate computation across the vision encoder, LLM, and action head. For perception-language reasoning, the scheduler selects a five-level Vision--LLM compute mode, from full recomputation to multi-step temporal reuse, based on visual-language representation stability. For action generation, it selects a three-level denoising mode, reusing intermediate denoising states during stable motion while preserving full refinement for goal-sensitive stages. By coordinating these decisions, ElegantVLA provides a general acceleration framework for modern VLA pipelines with explicit action-generation modules, without modifying or retraining the base model. Extensive experiments on GR00T, CogACT, and real-world tasks show that ElegantVLA preserves or improves task success while substantially accelerating inference. On GR00T, it achieves up to 2.55$\times$ average speedup. On CogACT, it delivers a 3.77$\times$ average speedup. In GR00T-based real-world experiments across six tasks, it reduces computation by 2.18$\times$ and increases control frequency from 13.8 Hz to 26.3 Hz.

Learned representations (or embeddings) are the foundation of modern machine learning systems, yet they are typically trained as fixed-size embeddings, without accounting for varying downstream resource or task constraints. Matryoshka Representation Learning (MRL) addresses this limitation by learning nested representations, but requires costly end-to-end retraining and does not support post hoc expansion, while Contrastive Sparse Representations (CSR) reduce training overhead via lightweight adaptors but operate at a 4x larger dimensionality. Additionally, all prior works restrict their framework towards compression only. In this work, we introduce \textbf{H}yperbolic \textbf{E}lastic \textbf{R}epresentation \textbf{L}earning (HERL), a framework for learning dimension-adaptive embeddings (compression and expansion) through a lightweight adaptor without retraining the base encoder. Our key idea is to exploit the exponential capacity of hyperbolic geometry by learning a non-linear mapping from the encoder space to hyperbolic space. We train a simple MLP to downsample the representations before projecting them onto a Lorentzian and learn adaptive representations that respect the Lorentzian geometry. Our approach is model-agnostic and effective in both supervised and unsupervised settings. Through extensive experiments across image and text modalities, we show that HERL preserves downstream performance across a wide range of embedding sizes, exhibits smooth interpolation between dimensions, and achieves these benefits at a fraction of the computational cost.

Touch is fundamental to dexterous manipulation, yet most egocentric human data increasingly used for robot learning lacks tactile information. Directly collecting large-scale tactile data is challenging due to sensor limitations, while human video data is abundant, contact-rich, and easily scalable. This motivates a natural question: can tactile signals be inferred purely from vision? To address this, we introduce **EgoTac**, a generalizable model that predicts rich **tac**tile information directly from **ego**centric human videos. EgoTac is trained on a unified corpus of over 5.7M image-tactile pairs, covering both continuous force measurements and binary contacts. By learning from this diverse dataset, EgoTac captures nuanced touch dynamics across varied interactions. Experiments demonstrate strong performance: in-domain prediction achieves an average force error below 0.06N. On out-of-domain contact prediction benchmarks, EgoTac consistently outperforms the state-of-the-art contact estimator. It also captures the rise and fall patterns of real tactile data and enables zero-shot predictions on unconstrained real-world videos. Scaling analyses further reveal that both data diversity and volume improve performance steadily. Overall, EgoTac provides a scalable pathway to extract tactile priors from egocentric human videos, enabling broadly applicable tactile-aware robot learning.

Continuous episodic memory is a core capability for autonomous agents operating in dynamic, real-world environments, yet current streaming video benchmarks provide limited tools for diagnosing what models remember and for how long. We introduce Egostream, a diagnostic benchmark for streaming episodic memory evaluation in egocentric vision. \egostream organizes 2,250 curated questions along seven cognitive dimensions: detail, spatial, temporal, event, social, causal, and prospective memory. We introduce the Answer Validity Window (AVW), which specifies the temporal span an answer remains valid as the observed scene evolves. This allows us to expand the questions into 8,528 recall-conditioned evaluations, enabling controlled testing from instant to ultra-long-term recall while separating genuine model forgetting from natural world-state changes. We rigorously establish baseline performance through a unified streaming MLLM framework that compares several state-of-the-art memory-management mechanisms, covering sliding windows, attention sinks, KV-cache pruning, merging, and offloading. Experiments within a unified Qwen3-VL backbone reveal that comparable aggregate accuracies mask starkly different memory profiles. For instance, token pruning preserves fine-grained details and temporal structure significantly better than token merging, while quantized offloading rescues ultra-long-term recall. Ultimately, all mechanisms operate well below real-time (>1s per frame), and top performing methods ceil at about 45\% accuracy, exposing critical gaps in current architectures. Egostream provides the diagnostic testbed needed to close these gaps.