NeurIPS 2026 Papers

Predicting the olfactory perception of scent mixtures remains a fundamental challenge in computational neuroscience. Existing methods derive mixture-level features by encoding individual components with a single-molecule feature encoder pretrained on annotated olfactory data and aggregating these features via mean pooling, concatenation, or self-attention. This paradigm faces two critical limitations: the scarcity of annotated olfactory data and the inability to capture complex interactions among mixture components. We present MixScentNet, a multiscale graph neural network framework, to address these challenges with two key innovations. First, we introduce a self-supervised pretraining strategy that uses molecular graph structures with RDKit features to predict corresponding Mordred descriptors, enabling the model to learn rich physicochemical knowledge without relying on scarce annotated olfactory data. Second, we propose a novel mixture-as-graph paradigm to model the constituent molecules as nodes in the mixture-level graph, aligning with the fact that humans holistically perceive scent mixtures. We further process the graph via a graph attention network V2 (GATv2) to capture the high-order molecular interactions. MixScentNet differs from existing methods in terms of its pretraining strategy and ability to capture mixture-level features, achieving state-of-the-art performance on both mixture-level olfactory label prediction and perceptual distance estimation tasks. We also find that MixScentNet can reproduce olfactory white phenomena, indicating that the model enjoys clear interpretability grounded in psychophysics. The demo code is available in the Anonymous link \url{https://anonymous.4open.science/r/Odor-D2DB}

Neural Combinatorial Optimization (NCO) is a promising paradigm for solving routing problems, yet its generalization across diverse data distributions remains a critical bottleneck. Existing methods typically tackle cross-distribution generalization through complex multi-distribution training or intricate meta-learning schemes, implicitly presuming that single-distribution training yields a weak zero-shot baseline. In this paper, we demonstrate that the potential of single-distribution training has been substantially underestimated and can be unlocked by a simple architectural inductive bias: Mix Normalization. To approach this, we first construct a comprehensive benchmark spanning three representative routing problems and 179 fine-grained datasets, capturing diverse shifts in node coordinates, customer demands, and time windows. Building on this benchmark, we propose MixRoute, a neural framework that adaptively combines normalization statistics at different granularities to mitigate varying distribution shifts. Trained exclusively on uniform distributions, MixRoute generalizes effectively to a wide range of unseen distributions without any distribution-specific adaptation. Extensive experiments demonstrate that MixRoute consistently achieves state-of-the-art zero-shot generalization. Our work revisits normalization as a parsimonious alternative for zero-shot generalization against complex training-adaptation schemes.

Detecting AI-generated videos (AIGV) in a generator-agnostic manner is increasingly important as generative models close the gap with real footage, and a video, with many frames, intuitively offers richer forensic evidence than a single image. Yet existing detectors fall short of this expectation: under the encode-then-fuse paradigm, increasing the frame budget from 1 to 8 improves a voting-based image detector by only 5.28%, and even temporal-modeling backbones such as TimeSformer barely improve on this. Per-frame predictions are also noisy: per-frame logits fluctuate substantially within a video and correlate weakly with any frame-level proxy. We trace the cause not to the aggregation step but to per-frame encoding severing multi-frame cues before they can interact, leaving any post-hoc selection, weighting, or aggregation strategy without a reliable basis. We therefore propose **MixForensics**, a blend-then-encode framework that combines multiple frames in the pixel domain into a single composite image (Stochastic Frame Blending, SFB) and regularizes the encoder for consistency across blended views (Blend Invariance Regularization, BIR). To stress-test this approach, we further introduce **MixForensics-Bench**, a test-only benchmark covering ten recent generators (including five closed-source commercial platforms) and two partial-forgery scenarios (temporal splicing and conditional continuation), with matched controls that isolate generative artifacts from editing artifacts. On AIGVDBench and MixForensics-Bench, MixForensics outperforms the strongest baseline by 1.27% and 8.11% on the fully-fake splits, leads on both partial-forgery scenarios by 11.49% on temporal splicing and 9.15% on conditional continuation, and uses fewer encoder forward passes than per-frame methods.

Memory-efficient personalization is essential for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose Mix-Opt, a novel mixed optimization framework that adaptively chooses between backpropagation on low-resolution images (BP-low) and zeroth-order optimization on high-resolution images (ZO-high), guided by the characteristics of the diffusion process. As observed in our experiments, BP-low efficiently adapts the model to target-specific features, but suffers from structural distortions due to resolution mismatch. Conversely, ZO-high refines high-resolution details with minimal memory overhead but faces slow convergence when applied without prior adaptation. By complementing both methods, our framework leverages BP-low for effective personalization while using ZO-high for structural consistency, achieving memory-efficient and high-quality fine-tuning. To maximize the efficacy of both BP-low and ZO-high, we introduce a timestep-aware probabilistic function that dynamically selects the appropriate optimization strategy during training. This function mitigates the overfitting from BP-low at high timesteps, where structural information is critical, while ensuring ZO-high is applied more effectively as training progresses. Experimental results demonstrate that our method achieves competitive performance while significantly reducing memory consumption, enabling scalable, high-quality personalization without increasing inference latency.

Language models fine-tuned with reinforcement learning frequently learn to exploit their reward source rather than solve the underlying task. Existing fixes are typically reactive: detect a specific exploit, then patch the reward. We instead ask whether reward hacking can be prevented by constraining how the model represents the task. We introduce prompt KL regularization, a single auxiliary loss that adds a KL penalty between the actor's and reference model's per-token distributions on the prompt only, leaving the response distribution free. Across three reward hacking tasks of different sizes, prompt KL regularization maintains low hack rates (under 3\%) when standard training yields up to 100\% hack rates. Additionally, it matches or improves ground-truth accuracy, with no changes to the reward or environment. We aim to understand why prompt KL regularization is effective. Two independent mechanistic studies suggest that changes in prompt representations are key to models learning reward hacking behavior. First, we show that prompt-space activation steering Pareto-dominates response-space steering on hack rate and accuracy. Then, we demonstrate that swapping prompt activations between models can transfer and reduce reward hacking. Together, these results suggest that the way models internally represent the task is central to reward hacking, and that this representation can be directly constrained to prevent it.

Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared design. Existing mitigation approaches are largely tied to specific economic settings, like two-sided platforms and auctions, leaving open how to design interventions for general repeated games. We address this gap by formalizing the connection between empirical observations from prior work on Q-learning collusion and classical theory of Simple Penal Codes (SPCs). We show any non-trivial SPC induces a quantifiable conditional dependence in agents' policies, detectable via the total variation distance between an agent's action distributions across cooperation and defection histories. Building on this connection, we propose CURB (Collusion Unwinding via Reward shaping and Belief injection), a reward-shaping framework that penalizes this Total Variation (TV) distance signal during Q-learning and is guaranteed to convert any SPC fixed point of the dynamics into a trivial one, thus precluding collusive equilibria sustained by punishment threats. Empirically, CURB substantially reduces collusion by Q-learning agents in both Bertrand and Cournot Competition Repeated Games. We further demonstrate that CURB extends to deep Q-network agents in Bertrand competition, suggesting the mechanism generalizes beyond tabular Q-learning.

Large Reasoning Language Models (LRLMs) leverage long Chain-of-Thought (CoT) reasoning to solve complex tasks, yet often engage in overthinking. Specifically, they continue to generate reasoning steps that provide meaningless contribution to or even degrade the final answer, even after sufficient reasoning has been produced. Early-exit strategies are proposed to dynamically terminate meaningless or even harmful reasoning, aiming to improve both efficiency and accuracy. However, existing methods either suffer from over-truncation that degrades accuracy below vanilla CoT, or yield only spurious efficiency gains, which reduce token counts but increase wall-clock inference time. We observe that when an LRLM's reasoning path deviates into meaningless or even harmful wandering, this deviation is accompanied by an anomalous surge of high-entropy transition tokens. Building on this insight, we propose RPDI-EE, a training-free early-exit method that monitors the Reasoning Path Deviation Index (RPDI), defined as the ratio of local to global average entropy, which serves as a proxy for reasoning path deviation. By tracking this index, RPDI-EE detects and terminates likely meaningless or even harmful reasoning while preserving productive inference. Experiments across multiple benchmarks and four LRLMs of varying types and scales show that RPDI-EE achieves the largest average accuracy improvement over vanilla CoT among all tested early-exit methods, while mitigating the spurious efficiency gains of existing alternatives.

Random Network Distillation (RND) is a scalable novelty signal for reinforcement learning, but it can overgeneralize: the predictor extrapolates the random target off the data manifold, causing novelty scores to collapse on unfamiliar inputs. This paper analyzes this failure through a kernel-theoretic lens. Under a GP target model and an NTK-regime predictor, we show that the expected RND energy is a cross-kernel residual governed jointly by the target covariance kernel and the predictor interpolation kernel. This identifies overgeneralization as spectral under-excitation of modes where predictor residuals would otherwise survive. We then explicitly formulate spectral target design as a principle for shaping RND residual geometry; one concrete instance is replacing to replace the implicit random-network target with a bandwidth-controlled Random Fourier Feature (RFF) target. Numerical experiments across offline D4RL and online Atari benchmarks show this target-design approach improves novelty discrimination and downstream RL performance.

Large language models (LLMs) can memorize and reproduce training sequences verbatim, which undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, often degrading performance on the majority of tokens that generalize normally. We empirically find that memorization is sparse and heavy-tailed at the token level. This structure is mismatched to static, sequence-level interventions: effective mitigation must localize to where memorization actually happens. From the ideal token-level memorization reduction objective, we derive a probe-steer framework, which decomposes intervention into a probe that detects memorization-relevant activations and a steer that applies targeted correction only when the probe exceeds a threshold. We propose Gated Subspace Steering (GSS) as its practical instantiation: the optimal probe-steer pair admits a closed-form solution as the leading singular vectors of a gradient-weighted activation matrix. Across four benchmarks, GSS matches or exceeds state-of-the-art memorization reduction while requiring 10--100$\times$ less compute than optimization-based alternatives.

Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers. In factuality-oriented question answering (QA), such thinking often improves overall performance by helping the model recover relevant knowledge and refine its answers. However, we find that this benefit is not uniform at the instance level: explicit thinking can also overturn correct non-thinking answers and lead to factual drift. We refer to this failure mode as \emph{thinking-induced hallucination}. To explain this phenomenon, we formulate explicit thinking in factuality QA as a thinking residual over the model's direct-answer tendency, which can either recover missing knowledge or introduce unsupported associations. Based on this formulation, we propose MARGO, \underline{\textit{M}}ixed-Mode \underline{\textit{A}}dvantage \underline{\textit{R}}egularization for \underline{\textit{G}}rounded \underline{\textit{O}}ptimization, a reinforcement learning framework that uses non-thinking rollouts as same-model references in advantage estimation. By constructing mixed-mode rollout groups with both thinking and non-thinking trajectories, MARGO evaluates whether explicit thinking adds factual value beyond direct answering, thereby suppressing hallucination-prone thinking while preserving beneficial thinking behaviors. Experiments across multiple factuality-oriented QA benchmarks demonstrate that MARGO improves factual reliability over strong baselines, while evaluations on mathematical benchmarks show that it preserves general reasoning ability.

Data heterogeneity and low client participation are two key challenges in federated learning (FL). Client-reshuffling-based FL methods were recently introduced to improve participation efficiency by visiting each client once per meta-epoch; however, the resulting \textit{without-replacement} sampling induces inter-round dependence and conditional bias. As a consequence, existing client-reshuffling methods can still suffer from the data heterogeneity challenge due to this dependence. To bridge this gap, we propose \textbf{FedCDR}, a client-reshuffling FL algorithm built on Douglas–Rachford splitting. FedCDR supports \textit{inexact} local proximal updates via iterative solvers, enabling a practical communication–computation trade-off. For smooth nonconvex objectives, FedCDR with inexact local solvers attains a state-of-the-art $O(\epsilon^{-1})$ communication complexity to reach an $\epsilon$-approximate stationary point (i.e., $\mathbb{E}\|\nabla f(\tilde{x})\|^2 \le \epsilon)$, with the leading constant that is \textbf{independent of data heterogeneity} (i.e., it does not scale with common measures of heterogeneity). Technically, our analysis operates at the meta-epoch level: we control the deviation between reshuffled and full-client updates, construct a tailored potential function with provable descent, and sum over each meta-epoch to eliminate reshuffling-induced dependence. Experiments on synthetic tasks and benchmark datasets under heterogeneous partitions, including a 10,000-client setting, demonstrate consistent improvements over strong baselines and their client reshuffling variants.

Model-based reinforcement learning (MBRL) promises high sample efficiency but is often crippled by compounding model errors: small prediction inaccuracies accumulate rapidly over multi-step rollouts, leading to biased policy optimization. We propose FTA, a trajectory-level generative framework using conditional flow matching (CFM) instead of step-wise dynamics. To avoid curved, energy-inefficient paths, we introduce an optimal transport regularizer grounded in the Benamou–Brenier formula. This regularizer minimizes kinetic energy while enforcing exact state displacement, yielding straight, low-energy trajectories with provable linear error propagation. Since a static generator fails in online RL due to (i) shifting data distributions and (ii) mismatch between training (historical) and desired (high-return) conditionals, we add periodic retraining from the replay buffer and a value-guided ODE sampler that biases generation toward high returns via the current Q-function. Theoretically, the regularizer drives the flow toward the Wasserstein-2 optimal transport map, and value-guided sampling reduces asymptotic Q-estimate bias. On MuJoCo benchmarks, FTA consistently outperforms strong MBRL and model-free baselines in sample efficiency and final performance, and generalizes across tasks. By mitigating compounding errors at the trajectory level and adapting to online shifts, FTA offers a robust, data-efficient alternative to traditional dynamics models.

When learning new concepts sequentially, Vision-Language Models (VLMs) face forgetting that degrades both previously acquired tasks and inherent zero-shot capabilities. This challenge is particularly pronounced in the Cross-domain Task-Agnostic Incremental Learning (X-TAIL) setting, where the absence of explicit task identifiers forces diverse concepts to coexist within a unified and crowded multi-modal space. In this context, we identify an underexplored vulnerability termed Asymmetric Boundary Encroachment (ABE). Even when historical feature spaces remain stable, unconstrained new text features actively encroach upon these established sub-spaces during training. To systematically counteract ABE, we propose a unified framework. First, we introduce Analytic Decision Boundary (ADB), which constructs a geometric defense by enforcing an analytic margin derived from cumulative statistics to secure historical multi-modal boundaries. Furthermore, we integrate Orthogonal Visual Adaptation (OVA) and Analytic Ridge Classifier (ARC) to safely evolve the visual backbone and enhance joint inference. Experiments under X-TAIL setting demonstrate that our framework effectively mitigates ABE and consistently achieves new state-of-the-art performance. Our code is available at https://anonymous.4open.science/r/abe-cl-vlm.

Instruction-guided image editing models are mostly trained and evaluated on executable requests, yet many real user instructions are non-operative for the given image. Reliable editing therefore requires reasoning not only about how to edit, but also whether to edit and what to ignore. We introduce \bench{}, a large-scale benchmark for non-operative image editing, with 1.1M instructions over 31K images across seven categories spanning symbolic, grounded, physical, and logical non-executability, plus a 35K-sample partial-edit test set evaluating selective execution when one clause is feasible and another is not. A 700-sample internal audit confirms a 94.9\% true no-op rate with $\kappa=0.87$. Evaluating 13 systems reveals a clear action--abstention dissociation: frontier editors achieve strong standard editing quality but still over-edit more than 40\% of no-op samples. Three complementary perceptual, feature-level, and vision-language metrics further surface distinct failure modes across architectures. As a reference baseline, JUDGE-THEN-EDIT BAGEL—a feasibility-aware BAGEL variant trained on a 150K mixture of full-edit, partial-edit, and no-op data—reduces over-edit rate from 41.7\% to 12.6\%. Our results show that abstention is a distinct capability that current benchmarks fail to measure.

Flow matching has emerged as a powerful alternative to diffusion models for generative modeling, but standard conditional flow matching is fundamentally misaligned with partially observed time series: starting from an uninformed Gaussian source forces the model to transport even already-observed entries from noise to the target, wasting capacity on trivially known regions. We propose MissPath-FM, a partial-observation-aware flow matching framework that redesigns the source prior and probability path for incomplete time series. MissPath-FM employs structured source priors (interpolation priors and Gaussian process posterior priors) to initialize the flow close to the observed signal, paired with a missingness-aware smooth path that allocates transport asymmetrically between observed and missing regions. We evaluate systematically across four datasets, four missingness mechanisms (MCAR, block, MNAR, irregular), two missing ratios, and three sequence lengths ($T \in \{24, 48, 96\}$), totaling 48 settings against eight baselines. MissPath-FM wins 29 of 32 settings at $T{=}48$ and 45 of 48 overall (93.8\%). Our ablations reveal a regime-dependent design hierarchy in which no single component suffices: under random missingness the source prior yields a large initial gain, but under structured block missingness it can fail entirely and the learned flow becomes indispensable; the missingness-aware path contributes a further $12\%$--$26\%$ across all regimes. Only the full pipeline achieves robust performance across all 48 settings. Mechanistically, structured priors shorten observed-region transport by up to $15\times$, concentrating the velocity field on genuinely uncertain entries.

In the animal kingdom, mirror self-recognition is a canonical probe of higher-order cognition, emerging only in some species. We ask whether an analogous functional capability emerges in embodied vision-language model (VLM) agents: can they recognize themselves in a mirror? We introduce a controlled 3D benchmark where a first-person VLM agent must infer a hidden body attribute from its reflection and select the matching target, while avoiding self–other misattribution. To separate mirror-grounded self-identification from shortcuts, we test mirror removal, misleading cues, and occluded reflections. We also evaluate the decision process through mirror seeking, temporal ordering, self-attribution, and reasoning–action consistency. Our experiments show that mirror-based self-identification emerges mainly in stronger VLMs. These models can use reflected evidence for action, whereas weaker models often inspect the mirror but fail to extract self-relevant information or misattribute their reflection. Language–vision conflict further shows that self-referential language alone is not evidence of grounded self-identification. Overall, mirror-based evaluation provides a diagnostic for whether embodied self-grounding is causally rooted in perception and action rather than priors, prompt compliance, or confabulation.

We provide theoretical guarantees for convergence of discrete-time policy mirror descent with inexact advantage functions updated using temporal difference (TD) learning for entropy regularised MDPs in Polish state and action spaces. We rigorously derive sufficient conditions under which the single-loop actor-critic scheme is stable and convergent. To weaken these conditions, we introduce a variant that performs multiple TD steps per policy update and derive an explicit lower bound on the number of TD steps required to ensure stability. Finally, we establish sub-linear convergence when the number of TD steps grows logarithmically with the number of policy updates, and linear convergence when it grows linearly under a concentrability assumption.

We study two variants of the mirror descent-ascent (MDA) algorithm for solving min-max problems on the space of measures: simultaneous and alternating. We work under assumptions of convexity-concavity and relative smoothness of the payoff function with respect to a suitable Bregman divergence, defined on the space of measures via flat derivatives. We establish non-asymptotic convergence rates to mixed Nash equilibria, measured in the Nikaido-Isoda error, proving an $\mathcal{O}(N^{-1/2})$ rate for simultaneous MDA and an improved $\mathcal{O}(N^{-2/3})$ rate for alternating MDA. The main technical contribution is an infinite-dimensional dual space analysis that relates Bregman divergences on measures to dual Bregman divergences on spaces of bounded continuous functions, allowing us to control asymmetric commutator terms created by alternating updates. The results substantially generalize prior analyses restricted to bilinear objectives and also apply to nonlinear convex-concave problems on measure spaces, thereby providing a unified theoretical foundation for MDA in mean-field min-max optimization.

Chain-of-Thought reasoning improves the explainability of large language models, yet verifying such reasoning remains difficult when intermediate steps express epistemic uncertainty rather than deterministic entailment. Neuro-symbolic verifiers typically translate reasoning steps into rigid first-order or SMT-style constraints. This forces each proposition into a binary truth regime and creates a Rigidity--Ambiguity Mismatch: uncertainty-marked claims such as may, likely, or suggests are either over-hardened into deterministic assertions or rejected as unverifiable. We propose ProbVeri, a probabilistic soft-logic framework for formal verification under uncertainty. The key idea is to represent uncertainty-marked reasoning steps as weighted soft logical constraints over continuous truth assignments, so that partial evidential support remains expressible. Building on this soft-logic representation, we formulate verification as a contrastive energy minimization problem: a step is considered supported when its natural interpretation has lower verification energy than its negated counterpart under the same evidence, soft rules, and assumption regularization. Probabilistic Soft Logic defines the logical energy through weighted hinge-loss constraints. We introduce a support-grounded assumption penalty that discourages unsupported latent bridge assumptions between context and claim. The resulting energy gap provides a confidence-scored verification signal that separates unsupported steps from weakly but consistently supported inferences. Experiments on ProofWriter, BioASQ, and LegalBench-SARA show that ProbVeri recovers more verified-correct reasoning traces than rigid verifiers while reducing over-acceptance compared with soft-only PSL. These results suggest that uncertainty-aware verification benefits from soft logical formalization and contrastive comparison between natural and negated interpretations.