ICLR 2026 论文列表

As an important branch of unsupervised learning, deep clustering has seen substantial progress in recent years. However, the majority of current deep clustering methods operate under the assumption of balanced or near-balanced cluster distributions. This assumption contradicts the common long-tailed class distributions in real-world data, leading to severe performance degradation in deep clustering. Although many long-tailed learning methods have been proposed, these approaches typically rely on label information to differentiate treatment across different classes, which renders them inapplicable to deep clustering scenarios. How to re-weight the training of deep clustering models in an unsupervised setting remains an open challenge. To address this, we propose a mini-cluster guided long-tailed deep clustering method, termed MiniClustering. We introduce a specialized clustering head that divide data into much more clusters than the target number of clusters. These predicted clusters are referred to as mini-clusters. The mini-cluster-level predictions serve as the guide for estimating the appropriate weights for classes with varying degrees of long-tailedness. The weights are then incorporated to re-weight the self-training loss in model training. In this way, we can mitigate model bias by re-weighting gradients from different classes. We evaluate our method on multiple benchmark datasets with different imbalance ratios to demonstrate its effectiveness. Further, our method can be readily applied to the downstream of existing unsupervised representation learning frameworks for long-tailed deep clustering. It can also adapt label-dependent long-tailed learning methods to unsupervised clustering tasks by leveraging the estimated weights. *The code is available in the Supplementary Material.*

Diffusion-based generative models have reformed generative AI, and have enabled new capabilities in the science domain, for example, generating 3D structures of molecules. Due to the intrinsic problem structure of certain tasks, there is often a symmetry in the system, which identifies objects that can be converted by a group action as equivalent, hence the target distribution is essentially defined on the quotient space with respect to the group. In this work, we establish a formal framework for diffusion modeling on a general quotient space, and apply it to molecular structure generation which follows the special Euclidean group SE(3) symmetry. The framework reduces the necessity of learning the component corresponding to the group action, hence simplifies learning difficulty over conventional group-equivariant diffusion models, and the sampler guarantees recovering the target distribution, while heuristic alignment strategies lack proper samplers. The arguments are empirically validated on structure generation for small molecules and proteins, indicating that the principled quotient-space diffusion model provides a new framework that outperforms previous symmetry treatments.

We study the problem of contextual online bilateral trade. At each round, the learner faces a seller-buyer pair and must propose a trade price without observing their private valuations for the item being sold. The goal of the learner is to post prices to facilitate trades between the two parties. Before posting a price, the learner observes a $d$-dimensional context vector that influences the agent's valuations. Prior work in the contextual setting has focused on linear valuation models, where valuations are linear functions of the context. We provide the first characterisation of a general nonparametric setting in which the buyer’s and seller’s valuations behave according to arbitrary Lipschitz functions of the context. We design an algorithm that leverages contextual information through a hierarchical tree construction and guarantees regret $\widetilde{O}(T^{(d-1)/d})$. Remarkably, our algorithm operates under two stringent features of the setting: (1) one-bit feedback, where the learner only observes whether a trade occurred or not, and (2) strong budget balance, where the learner cannot subsidize or profit from the market participants. We further provide a matching lower bound in the full-feedback setting, demonstrating the tightness of our regret bound.

The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for efficient resource allocation. This is challenged by: 1) the emergence phenomenon, where unpredictable capabilities appearing suddenly at critical model scales; and 2) uneven task difficulty and inconsistent performance scaling patterns, leading to high metric variability. Current prediction methods lack accuracy and reliability. We propose a Clustering-On-Difficulty (COD) framework for downstream performance prediction. The COD framework clusters tasks by their difficulty scaling features, thereby establishing a more stable and predictable subset that perform well-behaved scaling performance as compute increase. We adopt a performance scaling law to predict cluster-wise performance with theoretical support. Predictable subset performance acts as an intermediate predictor for the full evaluation set. We further derive a mapping function to accurately extrapolate the performance of the subset to the full set. Applied to an LLM with 70B parameters, COD achieved a 1.63\% average prediction error across eight key LLM benchmarks, offering actionable insights for resource allocation and training monitoring of LLMs pretraining.

Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as Best-of-N (BoN) and Rejection Sampling (RS) that make use of a verifier to enable test-time scaling. However, to date there is little theoretical understanding of how verifier *imperfection* affects performance — a gap we address in this work. Specifically, we prove that the instance-level accuracy of these methods is precisely characterized by the geometry of the verifier’s ROC curve. Our theory has two important takeaways, confirmed by experiments with Qwen and LLama models on GSM8K and MATH500. First, RS outperforms BoN for fixed compute, while both methods converge to the same accuracy in the infinite-compute limit. Second, it is generally impossible to predict the high-compute performance of either method based on observations in the low-compute regime.

Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about incomplete observations. In our empirical study, we identify key components when training early action prediction models. Our key contribution is a randomized training strategy that samples a time step separating observed and unobserved video frames, enabling a single model to generalize seamlessly across all test-time observation ratios. We further show that joint learning on both observed and future (oracle) representations significantly boosts performance, even allowing an encoder-only model to excel. To improve scalability, we propose a token masking procedure that cuts memory usage in half and accelerates training by 2× with no accuracy loss. Combined with a forecasting decoder, EAST sets a new state of the art on NTU60, SSv2, and UCF101, surpassing previous best work by 10.1, 7.7, and 3.9 percentage points, respectively. We support future research by releasing efficient training implementations and pre-trained models.

Recent progress in large reasoning models for challenging mathematical reasoning has been driven by reinforcement learning (RL). Incorporating long chain-of-thought (CoT) data during mid-training has also been shown to substantially improve reasoning depth. However, current approaches often utilize CoT data indiscriminately, leaving open the critical question of which data types most effectively enhance model reasoning capabilities. In this paper, we define the foundation model's reasoning potential for the first time as the inverse of the number of independent attempts required to correctly answer the question, which is strongly correlated with the final model performance. We then propose utilizing diverse data enriched with high-value reasoning patterns to expand the reasoning potential. Specifically, we abstract atomic reasoning patterns from CoT sequences, characterized by commonality and inductive capabilities, and use them to construct a core reference set enriched with valuable reasoning patterns. Furthermore, we propose a dual-granularity algorithm involving chains of reasoning patterns and token entropy, efficiently selecting high-value CoT data (CoTP) from the data pool that aligns with the core set, thereby training models to master reasoning effectively. Only 10B-token CoTP data enables the 85A6B Mixture-of-Experts (MoE) model to improve by **9.58\%** on the challenging AIME 2024 and 2025, and to raise the upper bound of downstream RL performance by **7.81\%**.

Deploying ML systems with only a few real samples makes operational metrics (such as alert rates or mean scores) highly unstable. Existing uncertainty quantification (UQ) methods fail here: frequentist intervals ignore the deployed predictive rule, Bayesian posteriors assume continual refitting, and conformal methods offer per-example rather than long-run guarantees. We introduce a forecast-first UQ framework that blends the empirical distribution with a frozen pretrained generator using a unique Dirichlet schedule, ensuring time-consistent forecasts. Uncertainty is quantified via martingale posteriors: a lightweight, likelihood-free resampling method that simulates future forecasts under the deployed rule, yielding sharp, well-calibrated intervals for both current and long-run metrics without retraining or density evaluation. A single hyperparameter, set by a small-$n$ minimax criterion, balances sampling variance and model--data mismatch; for bounded scores, we provide finite-time drift guarantees. We also show how this framework informs optimal retraining decisions. Applicable off-the-shelf to frozen generators (flows, diffusion, autoregressive models, GANs) and linear metrics (means, tails, NLL), it outperforms bootstrap baselines across vision and language benchmarks (WikiText-2, CIFAR-10, and SVHN datasets); e.g., it achieves $\sim$90\% coverage on GPT-2 with 20 samples vs.\ 37\% for bootstrap. Importantly, our uncertainty estimates are operational under the deployed forecasting rule agnostic of the population parameters, affording practicable estimators for deployment in real world settings.

Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work. In the meantime, recent Large Language Models (LLMs) excel at understanding scientific documents and generating high-quality code. Inspired by this, we introduce PaperCoder, a multi-agent LLM framework that transforms machine learning papers into operational code repositories. PaperCoder operates in three stages: planning, where it constructs a high-level roadmap, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files; analysis, which focuses on interpreting implementation-specific details; and generation, where modular, dependency-aware code is produced. Moreover, each phase is instantiated through a set of specialized agents designed to collaborate effectively across the pipeline. We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations, particularly from the authors of those papers, with author-released repositories as ground truth if available. Our results demonstrate the effectiveness of PaperCoder in creating high-quality, faithful implementations. Furthermore, it consistently shows strengths in the recently released PaperBench benchmark, surpassing strong baselines by substantial margins.

Image clustering is a fundamental task in visual machine learning. A key research direction in this field is the incorporation of prior knowledge. Recently, such prior knowledge has evolved from internal compactness constraints to external textual guidance. In particular, the introduction of textual modalities through CLIP has demonstrated impressive performance. However, CLIP is designed primarily for image–text alignment and may not be sufficient to capture clustering structures. Moreover, existing approaches often assume that textual features are universally beneficial, overlooking their varying suitability for different datasets. To address these issues, we propose to use spatial structure and selective text to jointly facilitate image clustering (SATC). Specifically, we design a graph attention network (GAT)-based encoder to capture relational dependencies among image patches, thereby extracting spatial features to facilitate clustering. In addition, we introduce a textual feature selector that uses the potential clustering compactness of textual features as the selection criterion and adaptively integrates them into the clustering process. Theoretical guidance is provided for this selector. Finally, the cluster assignment is produced through Tri-modal mutual distillation. Extensive experiments on 18 benchmark datasets demonstrate the effectiveness of SATC. The experimental results further verify the rationality of the textual feature selector. The code will be published.

Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers. Standard QA benchmarks, which typically assume a single gold answer, overlook this reality and thus produce inappropriate training signals. Existing attempts to handle ambiguity often rely on costly manual annotation, which is difficult to scale to multi-hop datasets such as HotpotQA and MuSiQue. In this paper, we present A$^2$Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. At its core is an automated pipeline that detects ambiguous questions and gathers alternative answers via trajectory sampling and evidence verification. The model is then optimized with RL using a carefully designed $\mathrm{AnsF1}$ reward, which naturally accommodates multiple answers. Experiments on eight open-domain QA benchmarks demonstrate that A$^2$Search achieves new state-of-the-art performance. With only a single rollout, A$^2$Search-7B yields an average $\mathrm{AnsF1}@1$ score of $48.4$% across four multi-hop benchmarks, outperforming all strong baselines, including the substantially larger ReSearch-32B ($46.2$%). Extensive analyses further show that A$^2$Search resolves ambiguity and generalizes across benchmarks, highlighting that embracing ambiguity is essential for building more reliable QA systems.

Large Language Models (LLMs) often experience compounding errors during long text generation. Early mistakes can propagate and lead to drift, faulty reasoning, or repetition. While scaling up models improves capabilities, it requires substantial computational resources, and the resulting self-correction behaviour remains unpredictable at inference time. Self-correction is a promising technique for addressing this issue. However, existing approaches have limitations. Supervised training methods can build self-correcting behaviours into models, but require training data collection and lack cross-domain generalizability. Current post-hoc iterative refinement methods operate only at inference time, but must wait for substantial portions of the draft to be generated before providing feedback. This feedback does not guarantee effective guidance, and the same mistake patterns can still reappear. In this paper, we introduce Once-More, a model-agnostic post-hoc self-correction framework that intervenes during generation. Once-More leverages token-level perplexity and feedback from verifiers to provide continuous guided steering of the generation path through a logit redistribution mechanism. This approach essentially helps accumulate "more correct" steps throughout the generation process. Evaluation on multiple benchmarks demonstrates that Once-More achieves state-of-the-art results compared to other self-correction methods. To our knowledge, Once-More is the first post-hoc method to leverage token perplexity and external feedback to perform continuous guided self-correction.

Offline–to–online deployment of reinforcement learning (RL) agents often stumbles over two fundamental gaps: (1) the sim-to-real gap, where real-world systems exhibit latency and other physical imperfections not captured in simulation; and (2) the interaction gap, where policies trained purely offline face out-of-distribution (OOD) issues during online execution, as collecting new interaction data is costly or risky. As a result, agents must generalize from static, delay-free datasets to dynamic, delay-prone environments. In this work, we propose $\textbf{DT-CORL}$ ($\textbf{D}$elay-$\textbf{T}$ransformer belief policy $\textbf{C}$onstrained $\textbf{O}$ffline $\textbf{RL}$), a novel framework for learning delay-resilient policies solely from static, delay-free offline data. DT-CORL introduces a transformer-based belief model to infer latent states from delayed observations and jointly trains this belief with a constrained policy objective, ensuring that value estimation and belief representation remain aligned throughout learning. Crucially, our method does not require access to delayed transitions during training and outperforms naive history-augmented baselines, SOTA delayed RL methods, and existing belief-based approaches. Empirically, we demonstrate that DT-CORL achieves strong delay-robust generalization across both locomotion and goal-conditioned tasks in the D4RL benchmark under varying delay regimes. Our results highlight that joint belief-policy optimization is essential for bridging the sim-to-real latency gap and achieving stable performance in delayed environments.

Recent incidents have revealed that large language models (LLMs) deployed in mental health contexts can generate unsafe guidance, including reports of chatbots encouraging self-harm. Such risks highlight the urgent need for rigorous, clinically valid evaluation before integration into care. However, existing benchmarks remain inadequate: 1) they rely on synthetic or weakly validated data, undermining clinical reliability; 2) they reduce counseling to isolated QA or single-turn tasks, overlooking the extended, adaptive nature of real interactions; and 3) they rarely capture the formal therapeutic structure of sessions, such as rapport building, guided exploration, intervention, and closure. These gaps risk overestimating LLM competence and obscuring safety-critical failures. To address this, we present \textbf{CareBench-CBT}, the largest clinically validated benchmark for CBT-based counseling. It unifies three components: 1) we provide thousands of expert-curated and validated items to ensure data reliability; 2) we include realistic multi-turn dialogues to capture long-form therapeutic interaction; and 3) we align all sessions with CBT’s formal structure, enabling process-level evaluation of empathy, therapeutic alignment, and intervention quality. All data are anonymized, double-reviewed by 21 licensed professionals, and validated with reliability and competence metrics. Evaluating 18 state-of-the-art LLMs reveals consistent gaps: high scores on public QA degrade under expert rephrasing, vignette reasoning remains difficult, and dialogue competence falls well below human counselors. CareBench-CBT provides a rigorous foundation for advancing safe and responsible integration of LLMs into mental health care. All code and data are released in the Supplementary Materials.

Reasoning LLMs suffer from quadratic compute growth as their context length increases, making reinforcement learning with verifiable rewards (RLVR) and test-time scaling prohibitively expensive. Prior work has tried to lighten the computational burden by shortening reasoning traces through pruning, summarization, or multi-stage training, but these methods remain bound to quadratic costs. We introduce Delethink, a thinking algorithm that realizes the Markovian Thinking Paradigm. Instead of producing one long monolithic reasoning trace, Delethink thinks in a sequence of chunks, the Delethink trace. Each chunk continues reasoning by referring only to a fixed number of prior tokens, which functions as a Markovian state sufficient for progressing reasoning, while deleting the rest. This preserves continuity without carrying the quadratic baggage. As a result, compute scales linearly and peak memory remains constant. In experiments, we show that Delethink can be applied directly to off-the-shelf reasoning models ranging from $1.5\textnormal{B}$ to $30\textnormal{B}$ parameters, with no loss in performance. Extended reasoning becomes possible under fixed memory and linear compute, while enabling efficient RL training on new tasks. On the DeepScaleR dataset, Delethink trains R1DistillQwen1.5B to the same benchmark performance as a standard long chain-of-thought (LongCoT) approach, where both models generate up to $24\textnormal{k}$ thinking tokens. The difference is efficiency. Delethink reasons $40\%$ faster with $70\%$ less memory footprint. By decoupling reasoning length from context length, the Markovian Thinking paradigm opens the door to next-generation reasoning LLMs that can scale to millions of tokens with linear compute and constant memory.

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) $\delta$-Guided Bit Switching ($\delta$-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2$\times$ speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be released to facilitate future research.

Correlation clustering is an important unsupervised learning problem with broad applications. In this problem, we are given a labeled complete graph $G=(V,E^+ \cup E^-)$, and the optimal clustering is defined as a partition of the vertices that minimizes the $+$ edges between clusters and $-$ edges within clusters. We investigate efficient algorithms to test the \emph{cost} of correlation clustering: here, we want to know whether the graph could be (nearly) perfectly clustered (with $0$ cost) or is far away from admitting any perfect clustering. The problem has attracted significant attention aimed at modern large-scale applications, and the state-of-the-art results use $\widetilde{O}({1}/{\varepsilon^7})$ queries and time (up to log factors) to decide whether a graph is perfectly clusterable or needs to flip labels of $\varepsilon {\binom n 2}$ edges to become clusterable. In this paper, we improve this bound significantly by designing an algorithm that uses ${O}({1}/{\varepsilon^2})$ queries and time. Furthermore, we derive the first algorithm that tests the cost for the special setting of correlation clustering with $k$ clusters with ${O}(1/{\varepsilon^4})$ queries and time for constant $k$. Finally, for the special case of $k=2$, which corresponds to the strong structure balance problem in social networks, we obtain tight bounds of $\Theta({1}/{\varepsilon})$ queries -- the first set of \emph{tight} bounds in these problems. We conduct experiments on simulated and real-world datasets, and empirical results demonstrate the advantages of our algorithms.

Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL fine-tuning requires abundant high-quality verifiable data, often obtained through human-annotated datasets and LLM-as-verifier loops. Both of these data types have considerable limitations: human-annotated datasets are small and expensive to curate, while LLM verifiers have high scoring latency and are costly to operate. In this work, we investigate the use of synthetic datasets in RL fine-tuning for multi-hop reasoning tasks. We discover that LLMs fine-tuned on synthetic data perform significantly better on popular real-world question-answering benchmarks, even though the synthetic data only contain fictional knowledge. On stratifying model performance by question difficulty, we find that synthetic data teaches LLMs to compose knowledge, which we to be a fundamental and generalizable reasoning skill. Our work thus highlights the utility of synthetic reasoning datasets in improving LLM reasoning capabilities.

The Iterative Markovian Fitting (IMF) procedure, which iteratively projects onto the space of Markov processes and the reciprocal class, successfully solves the Schrödinger Bridge (SB) problem. However, an efficient practical implementation requires a heuristic modification-alternating between fitting forward and backward time diffusion at each iteration. This modification is crucial for stabilizing training and achieving reliable results in applications such as unpaired domain translation. Our work reveals a close connection between the modified version of IMF and the Iterative Proportional Fitting (IPF) procedure-a foundational method for the SB problem, also known as Sinkhorn’s algorithm. Specifically, we demonstrate that the heuristic modification of the IMF effectively integrates both IMF and IPF procedures. We refer to this combined approach as the Iterative Proportional Markovian Fitting (IPMF) procedure. Through theoretical and empirical analysis, we establish the convergence of the IPMF procedure under various settings, contributing to developing a unified framework for solving SB problems. Moreover, from a practical standpoint, the IPMF procedure enables a flexible trade-off between image similarity and generation quality, offering a new mechanism for tailoring models to specific tasks.