NeurIPS 2026 Papers

Zero-shot mutation effect prediction is widely used to evaluate protein language models (PLMs). However, because existing benchmarks mix additive and non-additive mutations, and non-additive effects (epistasis) are sparse yet critical, it remains unclear whether these models truly capture thermodynamic residue coupling. As a result, strong overall performance may mask weaknesses in modeling multi-residue interactions. To make this distinction explicit, we introduce EpistasisBench, a thermodynamically stratified zero-shot benchmark constructed from large-scale stability measurements. By isolating significant and sign epistatic double mutations, it separates additive effects from thermodynamic coupling and defines two complementary tasks: ∆∆G prediction restricted to epistatic subsets, and a direct ∆∆Gint scoring task that examines non-additive structure in model probability space. When evaluated across more than 17 state-of-the-art PLMs, EpistasisBench reveals a consistent pattern. Performance declines under strict epistasis filtering, strong single-site predictors fail on coupled mutations, and standard masked language model scoring shows no variation in ∆∆Gint, thereby preventing detection of non-additive effects. Together, these findings indicate that the limitation lies in common zero-shot inference schemes rather than model capacity. To demonstrate that non-additive signal can in fact be recovered under a more suitable inference formulation, we introduce a simple joint marginal inference mechanism that restores non-additive signal and improves performance without fine-tuning. Overall, EpistasisBench provides a physically grounded test for multi-residue interactions and highlights a key gap in current zero-shot evaluation of protein language models. The dataset is available at https://www.openml.org/d/47245

Modern systems are often expected to transfer across tasks that were not specified during training, leading to the question: what data facilitates generalization in new, unanticipated settings? One hypothesis is that data with more structural information could contain shared circuits and subprograms that could be recycled in a wider array of downstream settings. Epiplexity, a recently proposed measure of the structural information a compute-bounded learner can extract from data, provides a mechanism to reason about this relationship. In this paper, we show how to operationalize epiplexity as an online training signal for data selection and generation. For selection, we fit scaling laws to the training loss curves of natural data domains to predict the expected epiplexity gain as a function of training tokens, and use this signal to adaptively determine the sampling weights over domains during training. For synthetic data generation, we define a generator's reward as the change in learner epiplexity over a buffer of previously generated data and use REINFORCE policy gradients to guide the generator toward an epiplexity-maximizing distribution. In both cases, higher epiplexity predicts improved downstream performance on zero-shot and fine-tuning based tasks, supporting the hypothesis that data rich in structural information yields representations that transfer across domains.

Mapping fine-scale 3D chromatin landscapes is critical for understanding gene regulation, yet the resolution of Hi-C data remains fundamentally constrained by both physical bottlenecks and sequencing costs. Although deep learning has shown promise in super-resolving Hi-C data, existing methods suffer from absolute coordinate loss during localized patching and a lack of structural and epigenomic priors in unconditioned generation. We propose a novel epigenomics-guided flow matching framework EpiFlow for 3D genome super-resolution. EpiFlow introduces two key innovations: (1) an EpiCond module that deterministically maps 1D epigenomic features to 2D spatial constraints via orthogonal expansion with built-in positional grounding, avoiding quadratic attention complexity; and (2) a Toeplitz-regularized classifier-free guidance mechanism that enforces distance-decay priors using a learnable symmetric prototype matrix. Extensive evaluation shows that our method achieves state-of-the-art cross-cell-type loop detection, improving recall by $2.8\times$ over raw Hi-C on unseen H1-hESC (Loop $F_1$ of $0.325$ vs. $0.199$) and outperforming all baselines on same-cell HFFc6 ($F_1=0.520$). Aggregate Peak Analysis (APA) confirms biological validity, and strong generalization to a held-out cell line demonstrates that the model learns transferable principles of 3D genome folding rather than cell-specific biases.

Latent world models based on Joint-Embedding Predictive Architecture (JEPA) are deterministic by design. While successful in fully observable scenarios, this paradigm breaks down when past observations and actions lead to multiple plausible future possibilities, e.g., due to occlusion. We introduce EpicWorldModel, a framework to train stochastic JEPAs for environments and tasks with inherent uncertainty under partially observability. We jointly train the EpicWorldModel predictor with its latent representation space to directly predict multiple potential future states using a flow-matching objective, when the goal-relevant scene content is absent from the conditioning history. We show that flow predictive variance approximates an upper bound on Expected Information Gain and serves as a useful exploration guidance for planning. By incorporating this uncertainty signal into Cross-Entropy Method (CEM)-based planning, our approach balances goal-reaching with exploration of uncertain regions where occluded or unseen goals are most likely to be located. We demonstrate the effectiveness of EpicWorldModel through a series of latent planning experiments with the best performance among all baseline methods, showing up to $22\%$ empirical improvement in success rate over LeWorldModel.

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.

The simplex method is one of the most widely used algorithms for linear programming, but its practical efficiency is highly sensitive to pivot selection and difficult to predict due to structural uncertainty in the search process. We propose EpiPivot, which casts pivot selection as a controllable decision process under epistemic uncertainty. EpiPivot identifies this uncertainty as two-dimensional: temporal dependence across the optimization trajectory and joint uncertainty across candidate pivot rules, and addresses both through temporal attention and an Epistemic Neural Network with shared latent sampling. At decision time, Thompson sampling combines these uncertainty-aware predictions into robust pivot choices. EpiPivot achieves significant improvements over classical and learning-based baselines, reducing pivot cost by up to 79\% over the best-performing classical rule on large-scale instances where most classical rules fail to converge within the time limit.

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/

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by selectively updating cached states, but their decision overhead scales with context length or model depth. We propose EntropyCache, a training-free KV caching method that uses the maximum entropy of newly decoded token distributions as a constant-cost signal for deciding *when* to recompute. Our design is grounded in two empirical observations: (1) decoded token entropy correlates with KV cache drift, providing a cheap proxy for cache staleness, and (2) feature volatility of decoded tokens persists for multiple steps after unmasking, motivating recomputation of the $k$ most recently decoded tokens. The skip-or-recompute decision requires only $O(V)$ computation per step, independent of context length and model scale. Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves 15.2×–26.4× speedup on standard benchmarks and 22.4×–24.1× on chain-of-thought benchmarks against vanilla baselines, with competitive accuracy and decision overhead accounting for only 0.5% of inference time.

Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distribution shifts can cause feature clusters corresponding to distinct classes in the model’s representation space to merge, while the decision boundary remains fixed. This induces a systematic skew in the predicted class distribution, referred to as prediction bias. Prediction bias refers to a shift in the predicted class distribution, with some classes overrepresented and others suppressed. We show that entropy minimization amplifies this prediction bias by tightening the existing clusters, reinforcing the incorrect groupings until all predictions collapse to a trivial solution. Next, to demonstrate the significance of prediction bias and mitigate it, we further propose Distribution Shift Bias Reduction (DSBR), a bias-correcting objective that specifically targets this failure mode by equalizing the contribution of each predicted class to the unsupervised entropy minimization loss. To study this failure mode, we design suitable adaptation settings using four medical‑imaging datasets and additionally evaluate on ImageNet‑C. We find that DSBR consistently stabilizes test‑time adaptation, prevents model collapse, and matches or outperforms the state‑of‑the‑art methods. Moreover, DSBR operates solely at test-time.

Patch-based transformers have emerged as efficient and improved long-horizon modeling architectures for time series modeling. Yet, existing approaches rely on temporally-agnostic patch construction, where arbitrary starting positions and fixed lengths fracture temporal coherence by splitting natural transitions across boundaries. This naive segmentation often disrupts short-term dependencies and weakens representation learning. We propose a novel Entropy-Guided Dynamic Patch Encoder (EntroPE), as a temporally informed framework that dynamically detects transition points via conditional entropy and dynamically places patch boundaries. This preserves temporal structure while retaining the computational benefits of patching. EntroPE consists of two key modules, namely an Entropy-based Dynamic Patcher (EDP) that applies information-theoretic criteria to locate natural temporal shifts and determine patch boundaries, and an Adaptive Patch Encoder (APE) that employs pooling and cross-attention to capture intra-patch dependencies and produce fixed-size latent representations. Extensive experiments on long-term forecasting, classification, and anomaly detection demonstrate that the proposed method improves both accuracy and efficiency, establishing entropy-guided dynamic patching as a promising new paradigm for time series modeling.

Agentic large language models are increasingly used to solve real-world tasks by reasoning over goals, invoking tools, and interacting with external environments. Reinforcement learning provides a natural framework for improving these behaviors, and recent agent RL methods have achieved strong results across domains. However, the training dynamics of agent RL remain poorly understood, limiting our ability to diagnose instabilities and design more effective training algorithms. In this work, we identify a previously underexplored phenomenon in agent RL, which we term \emph{cyclical entropy eruption}. Unlike single-turn reasoning RL, where entropy typically collapses and stays low, agent RL training exhibits unique recurring cycles of sharp entropy eruption and gradual subsidence. We decompose this dynamic into three phases and provide theoretical and empirical analyses of each, explaining the mechanisms underlying its cyclical oscillation. We further show that degenerate patterns such as sentence duplication and hallucination, once acquired during eruption, can persist and accumulate across cycles. Motivated by these findings, we propose SEAL (Separation-Enhanced Agent Learning), a lightweight auxiliary loss that separates correct and incorrect trajectories in representation space, directly targeting the root cause of entropy eruption. Experiments across multiple benchmarks, models, and RL algorithms demonstrate that SEAL stabilizes training and yields stronger downstream agent performance.

Large Language Models (LLMs) often generate factually incorrect outputs, commonly termed hallucinations, that undermine trust and limit deployment in high-stakes settings. Existing hallucination detection methods typically require multiple forward passes, or access to model internals. In this work, we provide theoretical background and empirical evidence that the *distribution* of token-level entropies, beyond the mean captured by perplexity or length-normalised entropy, serves as a fingerprint of hallucination, with distributional shape and tail behaviour carrying substantial independent signal. We formalize hallucination detection as a statistical hypothesis test and propose the **C**alibrated **E**ntropy **S**core (**CES**), a lightweight algorithm requiring only a single forward pass and black-box access to token logits. CES combines the mean signal with the maximum signal of the generated entropy through a calibrated reference CDF, producing scores that are directly comparable across models and tasks. We establish finite-sample calibration guarantees via a novel random-length Dvoretzky--Kiefer--Wolfowitz inequality, and also prove that CES detects hallucinations with probability converging to one exponentially fast in the generation length. Across eight QA benchmarks and ten generator models spanning open-source and API access models, CES achieves the highest detection performance among all single-pass black-box methods while providing formal error guarantees that existing heuristics lack. Remarkably, CES is statistically indistinguishable from multi-sample methods that require far greater computational cost, closing the gap between lightweight and expensive detection and making it suitable for real-time, large-scale deployment.

Simulating trajectories of multi-particle systems on complex energy landscapes is a central task in molecular dynamics (MD) and drug discovery, but remains challenging at scale due to computationally expensive and long simulations. Previous approaches leverage techniques such as flow or Schrödinger bridge matching to implicitly learn joint trajectories through data snapshots. However, many systems, including biomolecular systems and heterogeneous cell populations, undergo *dynamic* interactions that evolve over their trajectory and cannot be captured through static snapshots. To close this gap, we introduce **Entangled Schrödinger Bridge Matching (EntangledSBM)**, a framework that learns the first- and second-order stochastic dynamics of interacting, multi-particle systems where the direction and magnitude of each particle's path depend dynamically on the paths of the other particles. We define the Entangled Schrödinger Bridge (EntangledSB) problem as solving a coupled system of bias forces that *entangle* particle velocities. We show that our framework accurately simulates heterogeneous cell populations under perturbations and rare transitions in high-dimensional biomolecular systems. Anonymous code is provided at https://anonymous.4open.science/r/EntangledSBManon.

Combining the predictions of multiple models is one of the most effective strategies in machine learning. Thus, it is only natural to investigate the ensembling of language models (LMs). However, because LMs define distributions over strings, a proper ensemble requires aggregating predictions at the string level, which requires a computation that is generally intractable. In this work, we cast LM ensembling as an inference problem and propose the deployment of sequential Monte Carlo (SMC), an appropriate approximate inference scheme. Concretely, we introduce a unified framework for composing multiple LMs into ensemble distributions parameterized by a broad family of aggregation functions. To sample from these distributions, we introduce an SMC algorithm that operates in a shared character space, enabling ensembles of models with mismatching vocabularies and consistent sampling in the limit. We evaluate a range of ensembles across prompt and model combinations for various text generation tasks, finding that consensus-seeking strategies such as the product consistently outperform probability averaging, and that better posterior approximations can yield better ensemble performance.

Accurate time-series forecasting is critical for a wide range of problems involving temporal data. Ensemble modeling is a well-established technique for leveraging multiple predictive models to increase accuracy and robustness, as the performance of a single predictor can be highly variable due to shifts in the underlying data distribution. This paper proposes a new methodology for building robust ensembles of time series forecasting models. Our approach uses Adaptive Robust Optimization (ARO) to construct a linear regression ensemble whose model weights adapt over time. We demonstrate the effectiveness of our method through a series of synthetic experiments and real-world applications, including air pollution management, energy consumption forecasting, and tropical cyclone intensity forecasting. Our results show that our adaptive ensembles outperform the best ensemble member in hindsight by 16-26\% in root mean square error and 14-28\% in conditional value at risk and improve over competitive ensemble techniques.

We study zeroth-order optimisation under context distributional uncertainty, a setting commonly tackled using Bayesian optimisation (BO). A prevailing strategy to make BO more robust to the complex and noisy nature of data is to employ an ensemble as the surrogate model, thereby mitigating the weaknesses of any single model. In this study, we propose a novel algorithm for Ensemble Distributionally Robust Bayesian Optimisation that remains computationally tractable while managing continuous context. We obtain theoretical sublinear regret bounds, improving current state-of-the-art results. We show that our method’s empirical behaviour aligns with its theoretical guarantees.

Speech large language models (SpeechLMs) can process spoken requests, yet still lag behind text-prompted large language models (LLMs) on instruction following and reasoning. We argue that this gap is not only an ASR or representation problem: the same semantic instruction can induce different response policies when spoken with different speakers, accents, noise conditions, prosody, or disfluencies. We propose Verifiable Invariant Reinforced Behavior Alignment (VIRBA), a reinforcement-learning framework for aligning SpeechLM behavior across acoustic realizations of the same semantic intent. VIRBA builds multi-view spoken instruction groups, scores sampled responses with semantic preference, rule-verifiable correctness, cross-acoustic invariance, and adaptive reasoning rewards, and optimizes the model with Cross-Acoustic Group Relative Policy Optimization (CA-GRPO). The resulting objective moves SpeechLM alignment beyond teacher imitation toward robust reasoning policies that remain stable across realistic spoken realizations. Experiments with recent SpeechLM baselines, disfluency robustness, spoken QA, audio reasoning, and speech-to-text translation show the largest gains on reasoning-heavy and acoustically perturbed spoken prompts.

We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray embeddings, into a set-based diffusion model capable of jointly processing variable numbers of reference and target views. This formulation enables robust occlusion handling, reduces hallucinations under low-signal conditions, and improves photometric fidelity in visual content restoration. A unified set mixer performs global token-level attention across all input views, supporting scalable multi-camera enhancement while maintaining computational efficiency through latent-space supervision and selective decoding. Extensive experiments on EUVS, Para-Lane, nuScenes, and DL3DV demonstrate significant gains in perceptual fidelity, structural similarity, and robustness under severe extrapolation. SetDiff establishes a state-of-the-art diffusion-based solution for realistic and reliable novel-view synthesis in autonomous driving scenarios.

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.