NeurIPS 2026 Papers

Active feature acquisition (AFA) requires an agent to choose a budget-limited set of costly features before making a prediction. Greedy conditional-mutual-information (CMI) and value-of-information policies perform well when useful features are individually informative, but fail under joint-only evidence: a query is valuable only because it enables a future evidence set. To address this, we propose Forward-$\Phi$, a model-based non-myopic acquisition scorer that requires a known structural causal model (SCM) or generative AFA model. Forward-$\Phi$ evaluates a candidate query by its Shapley contribution to budget-feasible future action sets in a cooperative game on the expected forward utility. Two variants share the same game: a raw score that keeps both singleton and interaction value, and a residual score that strips the singleton component to isolate joint-only utility on diagnostic probes. On AFABench CUBE-NM, the raw Monte Carlo (MC) Forward Shapley scorer reaches $0.664 \pm 0.024$ accuracy over five MC seeds, well above all reported baselines including the OL-MFRL ($0.235$) and ODIN-MFRL ($0.160$) reinforcement-learning loops trained under the same split and shared pretraining protocol. Controlled SCM and Bayesian-network (BN) probes confirm the predicted mechanism: Forward-$\Phi$ yields substantial gains when target information is jointly carried, and matches Greedy on greedy-aligned controls. The primary contribution is the belief-conditional Forward Shapley state-action score, a credit-assignment signal derived from Shapley axioms for non-myopic AFA under joint-only evidence.

The uncertainty of a statistical model is most commonly factorized into an aleatoric and an epistemic part. This factorization changes how predictions are interpreted in downstream decision tasks. Importantly, except for the idealistic scenario with no model mismatch, the quantification is a characteristic of the model and not the data generating process. In this paper, we propose Forgetting to Improve a method that reduces this discrepancy by incorporating the task into the modeling framework. Our key insight is to acknowledge that in scenarios of model mismatch, data can have a detrimental effect on the modeling for a specific task. Based on this insight, we propose an influence function for Gaussian process models that allows for principled removal of detrimental data samples. We showcase the flexibility of this approach by demonstrating significant improvements across a range of tasks, including Bayesian optimization, model-based reinforcement learning, and transductive learning.

Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either static memory isolation or continuous online auditing, resulting in low memory efficiency and high computational overhead. To address these limitations, inspired by neuroscientific mechanisms that weak reactivation can destabilize memories and induce decay in the absence of reinforcement, we propose an agent-intrinsic training-free memory repair framework, \textbf{DREAM} (\textbf{D}ynamic \textbf{R}eactivation for \textbf{E}ngram \textbf{A}ttenuation in \textbf{M}emory), that enables selective functional forgetting of poisoned memories. Specifically, DREAM implements a three-stage pipeline: perturbation-induced implicit reactivation to reveal the structural fragility of malicious memories, adaptive anomaly diagnosis based on multi-dimensional activation patterns to detect topological anomalies, and a dynamic memory repair module that selectively suppresses harmful memories while reinforcing benign ones. Extensive experiments across diverse attackers and real-world tasks demonstrate that DREAM reduces attack success rates by over 95\% against backdoor poisoning while preserving strong benign utility. DREAM also achieves competitive robustness against injection attacks. In terms of runtime and token consumption, DREAM achieves up to a 2.13$\times$ speedup and a 37.7\% reduction in token consumption compared with A-MemGuard. Furthermore, DREAM also achieves a task success rate of 92.96\% on poisoned multi-agent systems.

Machine unlearning aims to remove the influence of selected training examples without full retraining. Standard evaluations often summarize unlearning quality with aggregate metrics, such as accuracy- and forgetting-based scores, which can hide localized failures. We study this failure mode at the example level by comparing the predictions of an unlearned model to those of the model retrained after deletion. We show that this pointwise discrepancy can be highly non-uniform: for gradient-ascent and random-labeling methods, with and without retain-set fine-tuning, it grows with geometric proximity to the forget set. We call this phenomenon *localized collateral forgetting*. Our analysis identifies a mechanism behind the effect: surrogate targets used during unlearning can be inconsistent with the local prediction structure induced by retraining, and this inconsistency propagates through shared representations to nearby examples. Motivated by this mechanism, we propose *Local Teacher Distillation*, a simple mitigation strategy that replaces random targets with soft labels from a small teacher trained only on retained neighbors of the forget set. On CIFAR-100 partial-class deletion, this local teacher brings the unlearned model substantially closer to retraining, especially near the forget set, while maintaining competitive aggregate unlearning metrics.

Multimodal large language models (MLLMs) are increasingly used for explainable image forgery analysis, where a shared decoder is expected to predict authenticity, localize evidence, and generate natural-language explanations. Existing methods typically rely on final decoder states, leaving open whether these late, language-oriented representations preserve localized manipulation cues. We test this assumption with a token- and layer-wise probing diagnostic that uses pixel-level masks only for analysis to separate tampered-region and authentic-region vision tokens. Across three MLLM-based forgery backbones and multiple manipulation types, we identify a mid-layer forgery evidence peak: tampered-region tokens are most linearly separable at upper-middle decoder layers and become less separable afterward, whereas authentic-region tokens continue to strengthen. This region-conditioned asymmetry suggests competition between localized manipulation cues and late semantic aggregation. Motivated by this diagnostic, we propose Gated Forensic Memory (\method), a lightweight evidence relay that reads from the diagnosed peak layer and writes re-encoded vision-token states back to late vision-token states through a zero-initialized gated residual. \method keeps the LLM frozen, adds no extra vision tokens, and requires no pixel-level training supervision. Across three backbones and seven benchmarks, \method improves authenticity prediction, explanation quality, and spatial alignment without mask supervision; the best read layer matches the diagnosed peak, turning the diagnostic into a practical layer-selection criterion.

Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. Still, most existing methods rely on Euclidean geometry to model intra-domain relationships. This approach can fail when features are only weakly related to the task of interest, leading to noisy, semantically misleading structure and degraded alignment quality. To address this limitation, we introduce FoSTA (Forest-guided Semantic Transport Alignment), a scalable alignment framework that leverages forest-induced geometry to denoise intra-domain structure and recover task-relevant manifolds prior to alignment. FoSTA builds semantic representations directly from label-informed forest affinities and aligns them via fast, hierarchical semantic transport, capturing meaningful cross-domain relationships. Extensive comparisons with established baselines demonstrate that FoSTA improves correspondence recovery and label transfer on synthetic benchmarks and delivers strong performance in practical single-cell applications, including batch correction and biological conservation.

Large vision-language-action (VLA) policies are increasingly trained as conditional generative models over action chunks, yet they typically improve by imitating the data they are given. This is limiting in deployment, where robots collect mixed-quality experience containing demonstrations, partial completions, recoverable mistakes, and failures. Full behavior cloning imitates failures, filtered behavior cloning discards useful sub-trajectories, and offline RL usually requires a large separate critic. We introduce ForesightFlow, a self-guided flow policy that augments each generated action chunk with a learned success-potential vector. The same flow therefore proposes candidate actions and scores them, enabling best-of-K inference without an external critic. The key challenge is that policy improvement and value calibration require different supervision: advantage weighting should suppress low-quality actions, but applying the same weights to the potential dimension removes the failure gradients needed for calibration. We address this with decoupled advantage-weighted flow matching, applying exponentiated advantage weights only to action velocities while training potential velocities uniformly. We also derive a single-step boundary estimator for conditional flow matching with independent endpoint sampling, allowing advantage computation with one stop-gradient forward pass. Across five BEHAVIOR-1K simulation tasks and five real-world bimanual tasks, ForesightFlow improves over imitation baselines, matches the strongest separate-critic baseline in average simulation success, improves real-world success, and reduces training compute by 38\%. Ablations show that decoupling prevents value hallucination, the one-step estimator preserves candidate-ranking fidelity, and self-guided sampling improves long-horizon performance.

Progress in language model development is often driven by comparative decisions: which architecture to adopt, which pretraining corpus to use, or which training recipe to apply. Making these decisions well requires reliable performance forecasts, yet the two commonly used signals are fundamentally limited. Cross-entropy loss is poorly aligned with downstream capabilities, and direct downstream evaluation is expensive, sparse, and often uninformative at early training stages. Instead, we propose to construct proxy metrics by aggregating token-level statistics, such as entropy, top-k accuracy, and expert token rank, from a candidate model's next token distribution over expert-written solutions. Across three settings, our proxies consistently outperform loss- and compute-based baselines: 1) For cross-family model selection, they rank a heterogeneous population of reasoning models with mean Spearman $\rho = 0.81$ (vs. $\rho = 0.36$ for cross-entropy loss); 2) For pretraining data selection, they reliably rank 25 candidate corpora for a target model at roughly $10{,}000\times$ less compute than direct evaluation, pushing the Pareto frontier beyond existing methods; and 3) for training-time forecasting, they extrapolate downstream accuracy across an $18\times$ compute horizon with roughly half the error of existing alternatives. Together, these results suggest that expert trajectories are a broadly useful source of signal for assessing model capabilities, enabling reliable performance forecasting throughout the model development lifecycle.

Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produce calibrated probabilities before outcomes are resolved. Memory provides a natural mechanism for transferring experience from resolved forecasts to future prediction tasks. However, existing agent-memory methods are not tailored to forecasting, as they typically store past interactions, reflections, or factual associations without explicitly representing reusable predictive factors or calibration knowledge. We propose ForecastCompass(FoCo), an adaptive factor-based memory framework for agentic forecasting. FoCo organizes forecasting experience with a hierarchical forecasting-task taxonomy, enabling retrieval task-relevant forecasting knowledge. It maintains two complementary memory components: factor memory, which captures reusable predictive dimensions, and reasoning memory, which encodes probability updating, uncertainty handling, and calibration principles. Using retrospective analyses as learning signals, FoCo iteratively revises memory through a verbalized memory-revision procedure, enabling the agent to accumulate transferable forecasting knowledge over time. Experiments on Prophet Arena and FutureX with GPT-5-mini and Gemini-2.5-Flash show that FoCo improves both probabilistic accuracy and calibration.

LLM benchmarks are usually consumed as scalar leaderboards, where adjacent ranks are read as adjacent capability differences. We argue that this display should be complemented rather than simply trusted or discarded: benchmark scores are useful summaries, but a sorted score table can overstate which model pairs are actually distinguishable. This limitation is especially clear for accuracy- and success-rate leaderboards, whose averages hide task-level structure, and it also appears in pairwise systems such as Elo-style ratings when pairwise evidence is compressed into a total order. We propose LLM tier ranking as a task-level reporting framework for benchmarks. Given benchmark outputs, we construct pairwise wins, losses, and ties between models on each task and aggregate them into ordered tiers using Selective Preference Aggregation (SPA). Cross-tier comparisons are reported only when supported by sufficient task-level agreement; models in the same tier are left unresolved, not declared equal. Across AIME 2025, $\tau$-bench airline, xbench DeepSearch, GDPVal, SWE-Bench Verified, and Chatbot Arena, tier ranking often preserves useful broad capability classes while abstaining from unsupported fine-grained distinctions among frontier models. In Chatbot Arena perturbation studies, tier outputs are more stable than Elo-style total orders, expressing weaker evidence through later tier separation rather than rank reshuffling. We recommend reporting tiered leaderboards, solution paths, top-tier size, singleton-winner thresholds, and pairwise resolution statistics alongside scalar scores.

While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.

Contact-rich manipulation requires precise control and complex physical interaction with the environment, posing significant challenges for robot policy learning. Vision-only policies struggle with such tasks, as contact states and force feedback are difficult to infer from vision alone. Existing methods mitigate this issue by incorporating force or tactile sensing. However, they often treat these signals as auxiliary observations rather than using them to model future interaction dynamics, leading to inefficient modality utilization and limited generalization. To address this, we propose ForceLDM, a force-aware latent dynamics model that enables the policy to anticipate future contact and motion dynamics in latent space and use them to guide action generation. Rather than predicting future observations in pixel space, which often requires large amounts of data and risk overfitting irrelevant details, ForceLDM learns a compact task-relevant representation through knowledge distillation. Specifically, a teacher network with privileged access to future force/torque and optical flow signals extracts future dynamic features, which are then distilled into a student network trained only on current observations. This enables the student to reason about upcoming contacts and physical dynamics at deployment without relying on future sensory inputs. To improve robustness and generalization, we further introduce a curriculum-based progressive noise injection strategy to mitigate over-reliance on future features. Experiments on five real-world contact-rich manipulation tasks demonstrate that ForceLDM significantly outperforms state-of-the-art baselines, generalizes effectively to novel objects, and remains robust to environmental perturbations.

Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision force feedback and control. Although recent efforts have attempted to integrate force/torque sensing into policies, how to build a simple yet effective framework that achieves robust generalization under multimodal observations remains an open question. In this paper, we propose **ForceFlow**, a force-aware reactive framework built upon flow matching. For contact-stage policy design, we investigate force signal fusion mechanisms and adopt an asymmetric multimodal fusion architecture that treats force as a global regulatory signal, combined with a joint prediction paradigm that enhances the policy's understanding of instantaneous force and historical information, thereby achieving deep coupling between force and motion. For task-level hierarchical decomposition, we divide manipulation into a vision-dominant approach stage (VLM-based pointing for target localization) and a touch-dominant interaction stage (force-driven contact execution), with a Vision-to-Force (V2F) handover mechanism that explicitly decouples spatial generalization from contact regulation. Experimental results across six real-world contact-rich tasks demonstrate that ForceFlow achieves a 37\% success rate improvement over the strong baseline ForceVLA while maintaining significantly lower cost. Moreover, ForceFlow exhibits accurate force signal prediction and demonstrates superior performance in contact force self-regulation and zero-shot out-of-distribution (OOD) generalization.

Forces and torques drive human motion, central to biomechanics, robotics, and physics-aware animation, yet they are often absent from learning-based motion pipelines for body reconstruction and generation. Some motion datasets provide force annotations, but the paired motion sequences are incompatible with the parametric body models used in modern learning pipelines. In addition, existing datasets typically obtain joint torques through inverse dynamics, which is inherently sensitive to the quality of the input kinematics; however, they do not quantify the reliability of these torque estimates. We close this gap with \textbf{ForceBody}, the first dataset to bring ground truth force supervision into a parametric body representation, shipped with per-sample torque uncertainty. ForceBody pairs the SKEL body model with ground reaction forces and inverse-dynamics joint torques across $10{,}389$ motion trials ($9.7$M frames, $27$ hours) from $140$ subjects. Each torque label is paired with a per-frame, per-joint uncertainty annotation obtained by Monte Carlo sampling through the inverse dynamics pipeline. We benchmark six architectures (MLP, Conv1D, LSTM, GRU, Mamba2, Transformer) on ground reaction force and joint torque prediction from SKEL motion. As one example use of the released uncertainty, finetuning a Transformer with per-sample uncertainty weighting reduces the MAE of joint torque estimation by $12\%$.

Follow the regularized leader (FTRL) is a foundational algorithm in online learning whose regret properties have been extensively studied for decades. However, in stark contrast to mirror descent---and gradient descent in particular---the convergence of FTRL to first-order stationary points in constrained nonconvex optimization was hitherto unresolved. In this paper, we show that continuous-time FTRL can fail to converge even asymptotically in constrained optimization problems; that is, the Karush-Kuhn-Tucker (KKT) gap of FTRL can remain bounded away from zero indefinitely. This is especially surprising in light of the fact that continuous-time FTRL guarantees a monotonic improvement of the objective value. As a result, we establish that non-convergent behavior of no-regret dynamics---which besets general variational inequality problems---can occur even in potential systems. From a technical standpoint, our construction relies on an infinitely differentiable function where the gradient flow dynamics exhibit decelerating oscillations without ever converging pointwise, which we in turn embed into higher-dimensional FTRL dynamics that sustain a perpetually large KKT gap.

Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation through examples. For deterministic interpolants, the velocity field is solely governed by a conditional endpoint mean; shifting this mean shifts the flow itself. This yields a simple principle for controllable generation: steer a pretrained model by changing the reference set it follows. We instantiate this idea in two forms. Reference-Mean Guidance is training-free: it computes a closed-form endpoint-mean correction from a reference bank and applies it to a frozen FLUX.2-klein (4B) model, enabling control of color, identity, style, and structure while keeping the prompt, seed, and weights fixed. Semi-Parametric Guidance amortizes the same idea through an explicit mean anchor and learned residual refiner, matching unconditional DiT-B/4 quality on AFHQv2 while allowing the reference set to be swapped at inference time. These results point to a broader direction: generative models that adapt through data, not parameter updates.

Therapeutic antibody screening requires prioritizing antibody candidates across specificity, affinity, and developability. Current pipelines typically silo these objectives and underuse structural information that governs antibody-antigen recognition. To address these inefficacies, we introduce FoldAbS, a unified supervised screening framework that reconceptualizes protein folding models as frozen foundation encoders, exploiting their internal representations to capture rich sequence, geometric, and interaction dynamics well beyond basic structure prediction. By coupling the folding model with lightweight, task-specific heads, FoldAbS seamlessly evaluates all three therapeutic criteria within a single architecture. Instantiating this framework with the open-source Protenix model (FoldAbS-Px) yields consistent improvements over baseline approaches, achieving significant performance gains of up to 13.1%, 9.2%, and 6.2% in specificity, affinity, and developability, respectively. Collectively, these results reposition protein folding models from structure predictors and confidence scorers into reusable foundation encoders for comprehensive and supervised antibody screening.

Cooperative multi-agent reinforcement learning (MARL) under sparse rewards remains fundamentally challenging because agents often fail to concentrate their influence, leading to insufficiently coordinated exploration. To address this, we propose the Focusing Influence Mechanism (FIM), a framework that encourages agents to focus their influence on under-explored parts of the state space through an entropy-based criterion, while leveraging eligibility traces to enable multiple agents to consistently align and sustain their influence on the same parts of the state space when beneficial, thereby promoting coordinated and persistent joint behavior. By emphasizing under-explored regions of the state space, FIM facilitates more efficient and structured exploration even under extremely sparse rewards. Across diverse MARL benchmarks, FIM consistently improves cooperative performance over strong baselines.

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality challenging. Existing methods mostly select historical frames based on attention scores, but their context decisions remain coarse. When multiple frames are generated in the same chunk, these methods often apply a shared history selection to the whole chunk, score historical frames solely by attention, and assign head-wise budgets either uniformly or by attention-pattern heuristics rather than explicit head-importance estimation. We show that frames within the same generated chunk can depend on distinct historical frames, that the same historical frame can receive different attention scores as its relative temporal distance to the current frames changes, and that masking different heads induces unequal generation degradation. Motivated by these findings, we propose \textbf{Focused Forcing}, a training-free KV selection method that focuses cached history along both generated-frame and head dimensions. For each generated frame, Focused Forcing preserves the most relevant and distinctive historical frames by combining attention scores with diversity scores of historical frames, while assigning larger budgets to heads with higher estimated importance. Across multiple autoregressive generation paradigms, Focused Forcing achieves up to $\textbf{1.48}\times$ end-to-end acceleration without training, while \textbf{improving visual quality and text alignment}. \textit{Our code will be released on GitHub.}