ICML 2026 论文列表

Inference-time scaling has recently emerged as a powerful paradigm for improving the reasoning capability of large language models. Among various approaches, \emph{Sequential Monte Carlo (SMC)} has become a particularly important framework, enabling iterative generation, evaluation, rejection, and resampling of intermediate reasoning trajectories. A central component in this process is the \emph{reward model}, which evaluates partial solutions and guides the allocation of computation during inference. However, in practice, true reward models are never available. All deployed systems rely on \emph{approximate reward models}, raising a fundamental question: \emph{Why and when do approximate reward models suffice for effective inference-time scaling?} In this work, we provide a theoretical answer. We identify the \emph{Bellman error} of the approximate reward model as the key quantity governing the effectiveness of SMC-based inference-time scaling. For a reasoning process of length $T$, we show that if the Bellman error of the approximate reward model is bounded by $O(1/T)$, then combining this reward model with SMC reduces the computational complexity of reasoning from exponential in $T$ to polynomial in $T$. This yields an \emph{exponential improvement} in inference efficiency despite using only approximate rewards.

Geometrical interpretations of deep learning models offer insightful perspectives into their underlying mathematical structures. In this work, we introduce a novel approach that leverages differential geometry, particularly concepts from Riemannian geometry, to integrate multiple models into a unified transfer learning framework. By aligning the Ricci curvature of latent space of individual models, we construct an interrelated architecture, namely Geometric Embedding Alignment via cuRvature matching in transfer learning (GEAR), which ensures comprehensive geometric representation across datapoints. This framework enables the effective aggregation of knowledge from diverse sources, thereby improving performance on target tasks. We evaluate our model on 23 molecular task pairs and demonstrate significant performance gains over existing benchmark models—achieving improvements of at least 14.4% under random splits and 8.3% under scaffold splits.

The Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) is a Bayesian nonparametric extension of the classical Hidden Markov Model, well-suited for learning from (spatio-)temporal data. To relax the restrictive geometric assumption on state durations, the HDP Hidden Semi-Markov Model was introduced. However, both models assume stationary state durations, which limits their expressive power. In this work, we extend the HDP-HMM framework by incorporating recurrent explicit duration modeling, resulting in a more general and flexible model: the Recurrent Explicit Duration HDP-HMM (RED-HDP-HMM). We propose a Gibbs sampling method for efficient inference in this model. Empirical results on both synthetic and real-world segmentation tasks demonstrate that RED-HDP-HMM consistently outperforms the disentangled sticky HDP-HMM and the standard sticky HDP-HMM.

Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in complex reasoning tasks and even leads to model collapse. Through a series of preliminary analyses, we reveal two problems: (1) data imbalance, where most training samples are simple, but the challenging yet crucial samples are scarce; (2) overthinking, where many undesired samples with redundant reasoning steps are used for self-training. To this end, we propose HSIR, which effectively Harnesses Self-Improvement in large Reasoning models via two simple-yet-effective approaches. Specifically, HSIR introduces a verify-then-exit sampling strategy to mitigate data imbalance by efficiently collecting more accurate solutions for difficult queries, and designs an Intrinsic Diversity score to quantify overthinking and filter out the undesired solutions. We apply HSIR to various post-training paradigms, among which we further propose H-GRPO, an enhanced GRPO algorithm that leverages the intrinsic diversity as an external reward to encourage concise and diverse reasoning via reinforcement learning. Extensive results show that HSIR not only effectively enhances the reasoning performance, i.e., bringing up to +10.9% average performance gains, but also significantly improves the reasoning efficiency by reducing up to 42.4% relative inference overhead.

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that **shifts from passive processing to active information foraging**. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively *contract* its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8 times. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost--capability trade-off in long-context reasoning. Resources are available at our [Project Page](https://xavierzhang2002.github.io/scout-page/).

Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key–value mapping at test time. However, our analysis reveals multiple phenomena that contradict this memorization-based interpretation. Motivated by these findings, we revisit the formulation of TTT and show that a broad class of TTT architectures can be expressed as a form of learned linear attention operator. Beyond explaining previously puzzling model behaviors, this perspective yields multiple practical benefits: it enables principled architectural simplifications, admits fully parallel formulations that preserve performance while improving efficiency, and provides a systematic reduction of diverse TTT variants to a standard linear attention form. Overall, our results reframe TTT not as test-time memorization, but as learned linear attention with enhanced representational capacity. Project page: https://research.nvidia.com/labs/sil/projects/tttla/.

Epistemic uncertainty quantification (UQ) for deep neural networks (DNNs) is a requirement for safe adoption of AI in mission-critical settings. Several leading methods for UQ linearize DNNs to form Bayesian Generalized Linear Models (GLMs), where epistemic uncertainty is modeled via the predictive posterior distribution. Linearizing around the parameters of the *final connected layer* of a DNN is a commonly used approximation for reducing the computational burden of such GLMs, though it is often believed to come at the cost of degraded performance. In this work, we compare GLMs arising from full-network and last-layer linearization using both theoretical and empirical approaches. We first employ tools from random matrix theory to conduct a theoretical comparison; this analysis reveals no meaningful improvement in the UQ capabilities of full linearization. Coupled with a large-scale empirical evaluation across a range of modern machine learning tasks, we arrive at the following conclusion: a last-layer approximation yields comparable UQ performance while offering substantially improved computational efficiency.

Retina-like event cameras and brain-inspired Spiking Neural Networks (SNNs) demonstrate exceptional energy efficiency through bio-inspired sensing and computation. While SNNs are naturally well-suited to the asynchronous nature of event data, their practical applications face the following challenges: sensitivity to noise, dense representations that disrupt spike pathways, and insufficient multi-scale feature perception. To address the aforementioned challenges, we propose a bio-vision-inspired object detection method motivated by biological (bio) vision systems. First, at the micro level, this paper proposes a noise-filtering STATNF-Neuron architecture to address the current sensitivity of basic neurons to noise. Based on STATNF-Neurons, the paper introduces two bio-vision-inspired macro-structures: Events-to-Spikes Representation (E2S), which preserves spiking characteristics while mimicking the memory and noise-filtering abilities of retinal neurons; Bidirectional Multi-Scale Spiking Network (BiSNet), which simulates cortical information flow pathways to integrate multi-scale features in both directions, enhancing the network's ability to perceive information at multiple scales. Extensive experiments show that the proposed bio-vision-inspired method achieving state-of-the-art performance. Notably, it reaches 96.1% accuracy on NCAR, 63.5% mAP(50) on N-Caltech101, and 69.1% mAP(50) on Gen1.

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention offers a direct view of grounding behavior. However, existing approaches typically rely on coarse summaries that fail to capture fine-grained instabilities in attention. Inspired by signal processing, we introduce a frequency-aware perspective on attention by analyzing its variation during generation. We model attention distributions as discrete signals and extract high-frequency components that reflect rapid local changes in attention. Our analysis reveals that hallucinated tokens are associated with high-frequency attention energy, reflecting fragmented and unstable grounding behavior. Based on this insight, we develop a lightweight hallucination detector using high-frequency attention features. Experiments on the RAGTruth and HalluRAG benchmarks show that our approach achieves performance gains over verification-based, internal-representation-based, and attention-based methods across models and tasks.

Spiking Neural Networks (SNNs) offer a notable energy-saving advantage compared to Artificial Neural Networks (ANNs) when deployed on neuromorphic hardware. While recent SNNs achieve superior performance using larger and deeper backbones, this comes at a cost of diminishing their energy-saving benefits. In this paper, we propose UniSparse, a unified sparsification framework for enhancing the energy efficiency of SNNs. We demonstrate that the affine parameters in batch normalization also serve as the learnable threshold of its subsequent spiking neurons. Based on this, we propose a novel spike sparsification method that reduces firing rate by constraining the affine parameters. As a complement to spike sparsification, we propose a weight pruning method based on the same energy constraint, which can be naturally integrated with spike sparsification. Experimental results demonstrate that UniSparse achieves a state-of-the-art trade-off between accuracy and energy efficiency across models and datasets. The sparsified ResNet-18 model requires only 7.04M SOPs for inference to achieve 92.38\% accuracy on the CIFAR-10 dataset. Our work highlights the great potential of deep SNNs in improving energy efficiency.

The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce **MEnvAgent**, a **M**ulti-language framework for automated **Env**ironment construction that facilitates scalable generation of verifiable task instances. MEnvAgent employs a multi-agent Planning-Execution-Verification architecture to autonomously resolve construction failures and integrates a novel Environment Reuse Mechanism that reduces computational overhead by incrementally patching historical environments. Evaluations on MEnvBench, a new benchmark comprising 1,000 tasks across 10 languages, demonstrate that MEnvAgent outperforms baselines, improving Fail-to-Pass (F2P) rates by **8.6%** while reducing time costs by **43%**. Additionally, we demonstrate the utility of MEnvAgent by constructing MEnvData-SWE, the largest open-source polyglot dataset of realistic verifiable Docker environments to date, alongside solution trajectories that enable consistent performance gains on SWE tasks across a wide range of models.

Programming-by-Example (PBE), as a typical few-shot inductive reasoning paradigm, aims to synthesize corresponding algorithms from a set of input-output examples. Although Large Language Models (LLMs) have demonstrated strong program synthesis potential, they still remain ineffective when handling complex PBE tasks. Specifically, LLMs often struggle to accurately grasp the underlying intent of examples, resulting in synthesized programs that either partially satisfy the examples or completely deviate from the target. To address these limitations, we introduce a process-supervised reinforcement learning method that provides fine-grained feedback during the synthesis process, improving the ability of LLMs to capture the intended behavior of provided examples. Firstly, we develop a reasoning tree construction method that is used to build a PBE process supervision dataset. Subsequently, we train a process reward model through preference learning to evaluate the effectiveness of reasoning steps. Finally, we introduce a curriculum learning strategy based on the difficulty of PBE tasks, using Proximal Policy Optimization (PPO) to optimize the model. Experimental results on representative PBE benchmarks show that our approach achieves an average pass rate of 56.61\%, significantly outperforming the state-of-the-art baseline by 8.73\%.

The population dynamics of molecules, cells, and organisms are governed by a number of unknown internal and external forces. In the last decade, population dynamics have predominately been modeled with Wasserstein gradient flows. However, since gradient flows minimize free energy, they fail to capture important dynamical properties, such as periodicity. In this work, we propose a change in perspective by considering population dynamics that minimize Wasserstein Lagrangian action, rather than free energy. As our main theoretical contributions, we derive the Hamiltonian equations of motion from the principle of least population-level action and we show that these mechanics encompass classical mechanics, quantum mechanics, and gradient flows. We further leverage the Hamiltonian perspective to propose an algorithm that learns the population mechanics from observed marginals, without specifying the Lagrangian. We demonstrate that by directly learning the population mechanics, our method forecasts and interpolates unseen marginals without a reference process, and outperforms gradient flow and flow matching methods across a wide range of real and simulated experiments.

Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories contain many related issues with shared structure or constraints. Existing methods typically rely on forward exploration, which operates under outcome uncertainty, incurs substantial inference-time overhead, and can drift from the final correct patch. We propose Conditional Reasoning Distillation (ConRAD), which leverages in-repository resolved issues by reconstructing repair reasoning backward from verified patches and distilling outcome-consistent, stage-wise repair reasoning plans. Injected at inference time, these plans guide fault localization and patch generation, replacing open-ended exploration with constrained inference without fine-tuning or search. On SWE-Bench Lite, ConRAD improves Pass@1 by 10.4\% (GPT-4o), 8.6\% (DeepSeek-V3), and 10.3\% (GPT-5), demonstrating a scalable inference-time alternative to forward exploration for long-horizon APR.

Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration methods focus on local information from the current action step and ignore the global context, leading to $>$20\% success rate drop and limited speedup in some scenarios. In this paper, we point out \textbf{spatial-temporal consistency} in VLA tasks: input images in consecutive steps exhibit high similarity, and propose the key insight that token selection should combine local information with global context of the model. Based on this, we propose ***SpecPrune-VLA***, a training-free, two-level pruning method with heuristic control. **(1) Action-level static pruning.** We leverage global history and local attention to statically reduce visual tokens per action. **(2) Layer-level dynamic pruning.** We prune tokens adaptively per layer based on layer-wise importance. **(3) Lightweight action-aware controller:** We classify actions as coarse- or fine-grained by the speed of the end effector and adjust pruning aggressiveness accordingly. Extensive experiments show that SpecPrune-VLA achieves up to 1.57× speedup in LIBERO simulation and 1.70× on real-world tasks, with negligible success rate degradation.

Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck, we propose a data-free knowledge distillation framework that generates LLM update vectors based on TinyLMs fine-tuned on private data. An update vector is a vector of parameter changes from an initial model to its fine-tuned version on a dataset, capturing the effect of cumulative gradient steps during fine-tuning. The key idea of our framework is a novel **Gradient Transformer** that transforms TinyLM's update vectors into LLM's update vectors. As derived from shadow datasets, $\texttt{Grad-Transformer}$ captures the correlation between TinyLM and LLM update vectors, enabling third-party providers to generate LLM update vectors given the organization's TinyLM update vectors without accessing the organization's private data. The framework supports multi-organization collaboration to jointly update LLMs, improving performance and cost-efficiency. Extensive experiments across language modeling and reasoning tasks show that $\texttt{Grad-Transformer}$ remarkably outperforms state-of-the-art knowledge distillation baselines, even under strict differential privacy protection.

Pre-trained models with parameter-efficient fine-tuning have shown strong effectiveness in Class-Incremental Learning (CIL), which seeks to balance model plasticity and stability. In this context, orthogonality constraints can significantly enhance model stability, yet their reliance on subspace inevitably compromises model plasticity over long tasks. To address this, we propose Gradient-Recycling Low-Rank Adaptation (GR-LoRA), which reconciles stability and plasticity by recycling the gradients discarded in orthogonal projection. Specifically, GR-LoRA recycles post-decomposition non-orthogonal gradient components into task-specific lightweight modules and selects optimal module via entropy to improve plasticity, while incorporating local and global mismatch suppression to preserve stability by synthesizing out-of-distribution representations across all tasks. Theoretical analysis confirms that this recycling strategy preserves stability and improves plasticity. Experimental results from multiple CIL benchmarks verify the effectiveness and general applicability of GR-LoRA.

Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (1) SFT excels at mimicking demonstration data, but can lead to problematic generalization as a form of behavior cloning. (2) Conversely, RFT can significantly enhance a model's performance but is prone to learning unexpected behaviors, and its performance is sensitive to the initial policy. In this paper, we propose a unified view of these methods and introduce Prefix-RFT, a hybrid approach that synergizes learning from both demonstration and exploration. Using mathematical reasoning problems as a test bed, we empirically demonstrate that Prefix-RFT is simple yet effective. Not only does it surpass the performance of standalone SFT and RFT, but it also outperforms parallel mixed-policy RFT methods. Our analysis highlights the complementary nature of SFT and RFT, validating that Prefix-RFT effectively harmonizes them. Further ablation studies confirm the method's robustness to variations in the quality and quantity of demonstration data.

While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limited by data annotations and evaluation metrics, fail to reliably distinguish between generic and highly detailed model outputs. To this end, this work introduces MECAT, a Multi-Expert Constructed Benchmark for Fine-Grained Audio Understanding Tasks. Generated via a pipeline that integrates analysis from specialized expert models with Chain-of-Thought large language model reasoning, MECAT provides multi-perspective, fine-grained captions and open-set question-answering pairs. The benchmark is complemented by a novel metric: DATE (Discriminative-Enhanced Audio Text Evaluation). This metric penalizes generic terms and rewards detailed descriptions by combining single-sample semantic similarity with cross-sample discriminability. A comprehensive evaluation of state-of-the-art audio models is also presented, providing new insights into their current capabilities and limitations. The code and data are publicly available at https://github.com/xiaomi-research/mecat.