NeurIPS 2026 Papers

Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. Existing augmentation methods, however, typically rely on heuristics and static paradigms. Motivated by dynamic data optimization, which shows that the contribution of samples varies across training stages, we propose OATS (Online Data Augmentation for Time Series Foundation Models), a principled strategy that generates synthetic data tailored to different training steps. OATS leverages valuable training samples as principled guiding signals and dynamically generates high-quality synthetic data conditioned on them. We further design a diffusion-based framework to produce realistic time series. Experiments on TSFMs demonstrate that OATS consistently outperforms regular training and yields substantial performance gains over static data augmentation baselines across six validation datasets and two TSFM architectures. The code is available at the link https://anonymous.4open.science/r/OATS-536E.

RNA function arises from a hierarchical folding process in which primary sequences form secondary structures that govern biological activity. While foundation models have proven effective for learning transferable RNA representations, most existing approaches rely on primary sequence alone or incorporate structural information only superficially during pre-training. Three problems limit current approaches: experimentally determined secondary structures are scarce, computational pseudo-labels are noisy, and no existing model integrates structure at multiple levels across masking, architecture, and supervision. Here, we present \textbf{N\"uwa.RNA}, a pre-trained foundation model built on a \emph{structure-driven multi-level pre-training framework} that integrates secondary structure at all three stages of pre-training simultaneously. N\"uwa.RNA introduces dual-granularity masking that combines single-token masking with structure motif masking, treating entire structural elements as indivisible units; a noisy structural attention bias that injects curriculum-corrupted contact maps into every Transformer layer to model pseudo-label uncertainty; and a structure denoising objective that recovers clean base-pairing states from corrupted input, completing a closed denoising loop. Pre-trained on a large-scale non-coding RNA corpus, N\"uwa.RNA achieves state-of-the-art performance on 10 of 13 BEACON benchmark tasks, with up to $+$7.83 F1 improvement on structure prediction, and attains the highest zero-shot secondary structure prediction accuracy among single-sequence RNA foundation models.

BFloat16 weights of large language models carry only ${\sim}10.5$ bits of information per 16-bit value, yet exploiting this redundancy on GPUs, where weights bottleneck both per-token bandwidth and concurrent capacity, has not produced wall-clock speedup. Existing variable-length lossless codes are compute-bound on SIMT decode. We present NyoomFloat12 (NF12), a lossless 12-bit fixed-length format for BF16 weights that addresses both bottlenecks. Over $99.7\%$ of trained BF16 weights have the upper four exponent bits set to $\texttt{0111}$ after a per-matrix power-of-two scale; dropping them yields a fixed-length 12-bit format with 16-instruction SIMT-friendly decode. Out-of-range groups reuse the encoded slot to index a per-matrix verbatim BF16 buffer at zero per-group storage overhead. In the bandwidth-bound regime, fused NF12 GEMV achieves up to $1.21\times$ matched-BF16 and $1.35\times$ cuBLAS, $71\%$ of the entropy-bound optimum (a hypothetical implementation reading the joint entropy floor at full HBM bandwidth). In the capacity-bound regime on Qwen3-32B, NF12's smaller footprint opens $4.5\times$ more KV-cache room; with decode at near-peak HBM bandwidth ($3.3\times$ faster than prior lossless decoders), NF12 raises throughput up to $2.67\times$.

The rapid progress of large language models (LLMs) is increasingly constrained by memory and deployment costs, motivating compression methods for practical deployment. Many state-of-the-art compression pipelines leverage the low-rank structure of trained weight matrices, a phenomenon often associated with the properties of popular optimizers such as Adam. In this context, Muon is a recently proposed optimizer that improves LLM pretraining via full-rank update steps, but its induced weight-space structure has not been characterized yet. In this work, we report a surprising empirical finding: despite imposing full-rank updates, Muon-trained models exhibit pronounced low-rank structure in their weight matrices and are readily compressible under standard pipelines. Motivated by this insight, we propose *NuMuon*, which augments Muon with a nuclear-norm constraint on the update direction, further constraining the learned weights toward low-rank structure. Across billion-parameter-scale models, we show that NuMuon increases weight compressibility and improves post-compression model quality under state-of-the-art LLM compression pipelines while retaining Muon's convergence behavior.

Adaptive decision-making in biological and artificial intelligence requires balancing the exploitation of known outcomes with the exploration of uncertain alternatives. Although prior work suggests that uncertainty generally promotes exploration, it has typically treated distinct sources of environmental uncertainty as equivalent. We consider environments with latent reward states that drift over time (volatility) and are observed through noisy outcomes (stochasticity). Both increase posterior uncertainty, yet we show they drive optimal exploration in opposite directions: volatility enhances it, stochasticity suppresses it. We establish this asymmetry formally by extending the Gittins index framework to Gaussian state-space bandits with latent dynamics. We further derive Cause-Aware Uncertainty-Sensitive Exploration (CAUSE), a closed-form exploration bonus obtained via control-as-inference that inherits the same monotonicities. CAUSE outperforms standard exploration strategies in environments with heterogeneous noise structure, and also improves on a Gittins-per-arm policy whose rested-bandit optimality does not transfer to restless settings. Learning and exploration are governed by the same noise-inference asymmetry, and the framework predicts that pathological noise inference produces reversed rather than merely impaired exploration, with implications for computational accounts of psychiatric conditions.

A central question in computational vision is whether human-like visual representations are better explained by discriminative or generative learning. Existing comparisons, however, often confound the learning objective with architecture, scale, and training data, leaving open whether the objective itself drives alignment. We address this confound using Joint Energy-Based Models (JEMs), which interpolate continuously between discriminative and generative training within a fixed architecture. By varying a single mixing coefficient, we isolate the effect of the learning objective and evaluate the resulting models across six human-alignment benchmarks spanning perceptual similarity, gloss perception, human response uncertainty, robustness, shape–texture cue conflict, and diagnostic feature attribution. Across this diverse suite, human alignment is consistently maximized at intermediate points of the generative–discriminative continuum, rather than at either endpoint. Hybrid JEMs combine the categorical structure induced by discriminative learning with the sensitivity to input structure induced by generative learning, yielding more human-like behavior across multiple levels of vision. These results suggest that the generative–discriminative dichotomy is the wrong axis for understanding human-aligned vision: alignment emerges not from choosing one objective over the other, but from balancing both.

Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing defenses span four stages---prior-training, in-training, post-training, and inference-time---and share one of two underlying strategies: either *suppress backdoor learning* (by filtering poisoned data or interrupting its acquisition during optimization) or *learn, then purify* (by repairing model weights or gating inputs after a fully backdoored model has formed). We propose a third strategy, *learn, but channel*: allow backdoor formation during training but route it into a designated, quarantined component that can be disabled at deployment. To this end, we propose **Q**uarantined **E**xpert **S**hutdown (QES), a computationally efficient containment strategy built in a regularization-steered MoE-like setting. Specifically, given a poisoned dataset, QES augments a Transformer-based language model with routed expert-specific LoRA branches and lightweight routers, and uses auxiliary routing objectives to attract trigger-conditioned behavior into a designated expert while preserving benign capability elsewhere. At deployment, mitigation reduces to a single constant-time operation: zeroing the quarantined expert's routing weight, without trigger screening or further updating model weights. Empirically, our methods reduce the attack success rate (ASR) from 100\% to 0-10\% on most settings across two tasks, three attacks, and four model families, while downstream utility is often preserved or only modestly affected. These results establish *learn, but channel* as a previously unexplored regime for backdoor containment in generative LLMs.

Reinforcement learning with verifiable rewards has made post-training effective when correctness can be verified automatically, but many useful model behaviors require satisfying several qualitative criteria rather than a single verifier. Rubric-based rewards extend RLVR to these open-ended domains by grading prompt-specific criteria and aggregating them into a scalar reward. However, the common static aggregations conflate a criterion's desired end-state importance with its current usefulness for learning. We show that this conflation is central in rubric RL: many criteria that matter to the final answer are already saturated or currently unreachable for the policy, while criteria with informative rollout variation are not reliably the ones assigned the largest human weights. We introduce a Policy-Aware Rubric Reward framework for RLVR, \textbf{POW3R}, that keeps human weights and reward category balance as the target objective while reallocating within-category training pressure toward criteria that distinguish the current rollouts. Across three base policies on each of two datasets spanning multimodal and text-only settings, POW3R takes first place on $27$ of $33$ (base policy, metric) cells we evaluate, leading both mean rubric reward and the harder strict ``every-rubric-passed'' pass-rate over vanilla GRPO with rubric-based rewards, and reaches the same plateau in $3$--$4\times$ fewer training steps. These findings suggest that rubric rewards should separate what should matter in the final answer from what can teach the current policy.

Continual tuning is essential for adapting multimodal large language models to evolving tasks and domains, yet existing methods often assume that every image-present example provides valid supervision for the visual pathway. We address the resulting gap: how to learn from all incoming multimodal instructions while preventing visually unnecessary supervision from drifting the visual interface. We propose Visual-Necessity-Gated Continual Tuning (VNG-CT), a path-aware framework that estimates sample-level dependence on visual evidence by comparing target likelihoods under the original image and a counterfactual null image. The resulting gate routes gradients to different parameter paths: all examples update the language path, visually necessary examples update the visual path, and low-necessity examples are absorbed by a lightweight calibration path that promotes invariance to irrelevant visual evidence. Across CoIN, MLLM-CL, and UCIT-style continual instruction streams, VNG-CT improves final and average performance while reducing visual forgetting. These results suggest that visual necessity offers a practical principle for stabilizing continual multimodal adaptation without discarding useful language-side supervision.

Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained text and vision encoders. The usefulness of such models have also been demonstrated on a wide range of benchmarks, with an important caveat - the dominant approach in these benchmarks evaluates multiple choice reasoning via text options. This is a natural way to test text-based reasoning in these models, and has led to significant insights regarding model behavior in the community. In this work, we ask a different question - what happens when the evaluation modality is visual, rather than text? We introduce three new vision-centric evaluation benchmarks in temporal frame retrieval, video future prediction, and causal memory distortion, all designed around evaluating visual understanding capabilities in large video models. Our approach complements the existing approaches to evaluate video understanding in frontier models. We show that current frontier models exhibit significant weakness when attempting to reason through visual queries, rather than text. We conclude with an extended analysis section that provides pointers for future improvements in visual understanding for large video models.

Multimodal Reinforcement learning with verifiable rewards (RLVR) algorithms assign the same advantage to every token in a generated sequence, providing no differential signal for tokens with varying degrees of dependence on visual evidence. A simple experiment confirms this issue: \textbf{scaling token advantages by uninformative random noise already outperforms uniform credit}, suggesting that uniform credit is empirically suboptimal. Beyond that, we observe RLVR tuning under uniform credit weakens visual grounding along three complementary axes: attention, gradient attribution, and functional dependence on image embeddings, \textbf{collectively indicating insufficient utilization of visual evidence}. To understand this degradation, we provide a theoretical analysis showing that, under language-prior dominance and regularity conditions, uniform credit can amplify a pretrained text-favored gradient imbalance, contributing to weaker visual attention. In response, we propose Hierarchical Context Credit Reassignment (\textbf{HiCCR}), which reassigns credit at two levels: a token-level weight amplifies the advantage for visually grounded tokens, and a trajectory-level weight upweights rollouts with stronger visual engagement. The entire mechanism \textbf{adds less than 3\% wall-clock overhead} and applies to mainstream RLVR algorithms without auxiliary models or additional data. On ten benchmarks spanning mathematical and general multimodal reasoning, HiCCR consistently improves upon its corresponding base algorithm and achieves state-of-the-art results among open-source models of comparable scale, while alleviating the weakening of visual grounding observed under RLVR training.

Class-incremental learning (CIL) with pre-trained models has increasingly adopted Mixture-of-Experts (MoE) adapters, which freeze the backbone and selectively route inputs to sparse adapter subsets, achieving competitive performance through efficient parameter reuse. However, as new tasks are learned sequentially, the router's output distribution gradually shifts away from previous states, undermining consistent adapter reuse and accelerating forgetting. Through a controlled instance-level analysis, we show that this effect is highly asymmetric, where instances with large routing drift account for most of the performance degradation, while those with small drift remain stable or can even benefit from it. This finding suggests that only excessive drift requires correction, while small drift may be better preserved than suppressed, and motivates us to propose Trust-Region Projected Routing (TRPR) that adapts the trust-region principle from constrained optimization to routing stabilization. It constrains each input's routing distribution within a KL-bounded trust region around a class-level anchor, correcting only excessive deviations while leaving small drift intact. To complement class-level anchoring with per-sample adaptability, TRPR additionally introduces an Instance-Adaptive (IA) path for fine-grained per-sample specialization, fused with the projected path via a learned gate. Extensive experiments on four CIL benchmarks show that TRPR consistently outperforms nine representative PEFT-based baselines, with accuracy gains of up to 3.06% in average and final accuracy and forgetting reduced by up to 2.48%.

Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correctness alone is not sufficient: mathematical proofs should also be clear, concise, insightful, and transferable to other problems. While this proof quality is subjective and depends on the reader and context, many of its components are concrete and broadly valued. In this work, we identify such components and introduce ProofRank, a benchmark curated from challenging mathematical competitions. ProofRank evaluates several scalable proxies of proof quality: (i) conciseness, measuring whether proofs avoid unnecessary steps; (ii) computational ease, measuring the extent to which a proof relies on tedious calculations; (iii) cognitive simplicity, measuring how accessible the used proof techniques are; (iv) diversity, measuring how varied a model's proofs for a single problem are; and (v) adaptivity, measuring whether a model can follow a specified proof technique. Across models, we find substantial differences in proof quality that are not captured by correctness-only benchmarks. We also observe significant trade-offs between proof-quality metrics and correctness, suggesting that future evaluations of mathematical reasoning should measure how useful LLM-generated proofs are.

Parameter-efficient image-to-video transfer adapts frozen image foundation models to video via lightweight trainable adapters. Existing methods insert the same adapter at every transformer layer, implicitly assuming all layers require equal temporal modeling. A layer-wise sensitivity analysis across four video-native model families and two pretraining paradigms reveals that this assumption is wrong: temporal sensitivity increases with depth, and the pretraining paradigm determines its growth profile. Vision-only models exhibit a gradual rise, while vision-language models show early suppression followed by late recovery. This finding motivates STRAP, a training-free adapter placement rule that derives a spatial-to-temporal transition boundary from a paradigm-matched video model. Spatial adapters are assigned before this boundary and temporal adapters after it, without modifying the adapter architecture itself. On four fine-grained action recognition benchmarks, STRAP improves accuracy by up to 11.8\% over uniform placement, reduces trainable parameters by 29 to 48\%, and lowers inference time by up to 10\%. On standard benchmarks, it matches accuracy with fewer parameters.

Multiple instance learning (MIL) learns from bag-level labels, but a bag’s label is often supported by only a few hidden instances. In heterogeneous bags, these useful instances are rare, diverse, and surrounded by many weak or noisy observations. We propose Sparse Support Grounding, a MIL framework that learns instance influence directly. The key idea is simple: an instance should not matter just because it can be matched somewhere; it should matter when the match provides reliable label evidence. Our method forms a compact, bag-specific evidence support, compares instances with label-consistent supports, and uses unbalanced transport to estimate how much source mass each instance should retain. This retained mass becomes the strength of its grounding signal, so reliable evidence shapes training more than nuisance content, while the bag classifier still uses the full bag. Thus, transport is turned from a matching rule into a way of learning which instances should drive supervision. Experiments on synthetic MIL, whole-slide images, and clinical endomicroscopy show consistent gains, with the largest improvements when sparse diagnostic evidence is embedded in heterogeneous nuisance content.

Providing external information beyond the query is a common way to improve large language model (LLM) inference, as seen in in-context learning (ICL), retrieval-augmented generation (RAG), and memory-based methods (Mem). Existing work increasingly suggests that useful external information should compensate for the gap between LLMs and user queries, implicitly assuming that stronger gap-correction can lead to better performance. In this paper, we challenge this assumption and show that more gap-corrective external information can instead harm performance. We analyze this phenomenon in Transformers through the lens of reasoning error, defined as the difference between the predicted answer vector and the ground-truth answer vector. Our analysis reveals that external information can be not only under-corrective but also over-corrective, where excessively strong correction increases reasoning error. We further show that the induced correction vector is jointly determined by attention and the complementarity between the external information and the query, and derive conditions under which information is properly corrective in both direction and magnitude. Experiments on four mainstream LLMs and seven reasoning benchmarks across ICL, RAG, and Mem validate our theory and support a theory-guided information selection method.

Diffusion-based models decompose sampling into many small Gaussian denoising steps—an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel predictor across the trajectory, forming an end-to-end network trainable from scratch or initializable from pretrained flow-matching models. Its exact trajectory likelihood further enables self-distillation: a lightweight denoiser trained on the model's own score produces high-quality samples in four steps. On text-to-image benchmarks, NTM matches or outperforms strong few-step baselines in just four sampling steps while uniquely retaining exact likelihood over the generative trajectory.

Generative models such as Diffusion Models and Flow Matching have improved multimodal trajectory planning in autonomous driving, but still suffer from inference latency and the lack of tractable probability densities, relying on heuristic trajectory selection. We propose BiDrive, a real-time end-to-end planning framework based on Normalizing Flows (NFs). By leveraging invertibility and exact likelihood estimation, BiDrive directly evaluates trajectory probabilities in a single forward pass, enabling principled maximum-likelihood-based decision making. To address the autoregressive bottleneck of expressive flows, we further develop a bidirectional distillation framework that compresses an autoregressive flow into a one-pass generator, achieving real-time inference (50 FPS) while preserving modeling capacity. The autoregressive model is used only during training as a probabilistic teacher. In addition, we introduce a latent-space optimization mechanism that incorporates differentiable safety and dynamic constraints for efficient test-time trajectory refinement. Experiments on NAVSIM closed-loop benchmarks demonstrate state-of-the-art performance in both safety and efficiency, highlighting the potential of Normalizing Flows for real-time trajectory planning. Code is available at: https://anonymous.4open.science/r/BiDrive.

Training large language models at 4-bit precision is critical for efficiency. We show that nGPT, an architecture that constrains weights and hidden representations to the unit hypersphere, is inherently more robust to low-precision arithmetic. This removes the need for interventions—such as applying random Hadamard transforms and performing per-tensor scaling calculations—to preserve model quality, and it enables stable end-to-end NVFP4 training. We validate this approach on both a 1.2B dense model and hybrid (Mamba-Transformer) MoE models of up to 3B/30B parameters. We trace this robustness to the dot product: while quantization noise remains largely uncorrelated in both standard and normalized architectures, the signal behaves differently. In nGPT, the hypersphere constraint enhances weak positive correlations among the element-wise products, leading to a constructive accumulation of the signal across the hidden dimension while the noise continues to average out. This yields a higher effective signal-to-noise ratio and a flatter loss landscape, with the effect strengthening as the hidden dimension grows, suggesting increasing advantages at scale. A reference implementation is available at https://github.com/anonymous452026/ngpt-nvfp4.