AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ICML 2026

Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning

Yike Zhao, Onno Eberhard, Malek khammassi, Ali H. Sayed, Michael Muehlebach

The family of linear recurrent neural networks has shown strong performance as recurrent memory units in partially observable reinforcement learning. We provide a theoretical justification for their empirical effectiveness by constructing and studying two linear filters: (i) the first exactly reproduces the pre–softmax logits of the belief vector in a hidden Markov model (HMM) under a deterministic transition matrix, thereby serving as a sufficient statistic for optimal policy learning, (ii) the second achieves vanishing state-decoding error under a nearly deterministic transition matrix, thus reducing state ambiguity to near zero. The results extend to action-controlled HMMs, where the corresponding linear filters become time-varying with action-dependent dynamics. We illustrate our main results through numerical experiments and further show that the constructed linear filter serves as a strong feature extractor in a small reinforcement learning game.

ICML 2026

Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization

Mengjingcheng Mo, Jiaxu Leng, Xinbo Gao

Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, where static sampling fails to disambiguate semantically distinct events. To overcome this, we propose $Anom\text{-}\pi$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process within a dynamic environment. Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy, utilizing temporal atomic operators such as local backtracking, temporal expansion, and fine-grained sampling to endow the model with perceptual proactivity. To learn such complex interaction strategies under video-level weak supervision, we design Interactive Direct Preference Optimization (iDPO) to achieve trajectory-level policy alignment, guided by an Active Evidence Inquiry (AEI) utility that balances task success, informative evidence acquisition, and interaction cost. This approach enables the agent to learn to actively disambiguate hypotheses while suppressing redundant exploration. Extensive experiments demonstrate that our framework, with only 2B parameters, achieves highly competitive performance, significantly outperforming state-of-the-art large-scale VAU models in complex scenarios.

ICML 2026

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu, Yinglong Xia, Qiang Zhang, Qifan Wang, Ren Chen, Dongqi Fu, Jiayi Liu, Zhuokai Zhao, Xiangjun Fan, Benyu Zhang, Yixin Chen

Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge. Prior work shows that fine-grained experts enlarge the space of expert combinations and improve flexibility, but they also impose substantial routing overhead, creating a new scalability bottleneck. In this paper, we explore a complementary axis for scaling—how expert outputs are aggregated. We theoretically show that replacing the standard weighted-summation aggregation with structural aggregation expands the expert-combination space without altering the experts or router, and enables possible multi-step reasoning within a single MoE layer. To this end, we propose DAG-MoE, a sparse MoE framework that employs a lightweight module to automatically learn the optimal aggregation structure among the selected experts. Extensive experiments under standard language modeling settings show that DAG-MoE consistently improves performance in both pretraining and fine-tuning, surpassing traditional MoE baselines.

ICML 2026

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

Helena Casademunt, Caden Juang, Adam Karvonen, Samuel Marks, Senthooran Rajamanoharan, Neel Nanda

Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying the training data, for example by adding data that better specify the intended generalization. However, this is not always practical. We introduce Concept Ablation Fine-Tuning (CAFT), a technique that leverages interpretability tools to control how LLMs generalize from fine-tuning, without needing to modify the training data or otherwise use data from the target distribution. Given a set of directions in an LLM's latent space corresponding to undesired concepts, CAFT works by ablating these concepts with linear projections during fine-tuning, steering the model away from unintended generalizations. We successfully apply CAFT to three fine-tuning tasks, including emergent misalignment, a phenomenon where LLMs fine-tuned on a narrow task generalize to give egregiously misaligned responses to general questions. Without any changes to the fine-tuning data, CAFT reduces misaligned responses by 10x without degrading performance on the training distribution. Overall, CAFT represents a novel approach for steering LLM generalization without modifying training data.

ICML 2026

Sketch-Based Low-Rank Model Merging with Shared Circulant Transforms

Zhiming Zhang, Rong Yin, Xiaoshuai Hao, Hansong Zhang, Hao Peng, Yong Liu, Can Ma, Dan Meng

Merging multiple low-rank adapters (LoRA) provides a practical route to scaling multi-task learning and deployment more efficiently than full-model weight merging, while avoiding reliance on task-specific training data. However, most existing approaches either treat LoRA updates as dense weight deltas or depend on expensive subspace factorizations, making the merge step a primary latency bottleneck. To address this issue, this paper establishes a theoretically positive relationship between merging quality and the effective rank of the matrices being merged. Motivated by this insight, we propose **CircuMerge**, a sketch-based framework for low-rank model merging built on shared circulant transforms. Especially, this approach treats each adapter as a pair of low-rank matrices and applies a shared circulant transform to align all tasks in a common coordinate system. This alignment enables more efficient sampling, allowing us to generate compact sketches that effectively summarize the interactions between tasks. These compact sketches enable applying the merging rules directly to them and reconstructing a standard low-rank adapter, preserving the essential information while significantly reducing computational overhead. Across a broad multi-task LoRA benchmarks covering both vision and language settings, extensive empirical results demonstrate that CircuMerge reduces the overall merging time by at least 44\% compared to the state-of-the-art approaches, with accuracy matching or exceeding the optimal level.

ICML 2026

The Realignment Problem: When Right becomes Wrong in LLMs

Aakash Sen Sharma, Debdeep Sanyal, Manodeep Ray, Vivek Srivastava, Shirish Karande, Murari Mandal

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make static alignment increasingly brittle. As policies evolve, deployed models can diverge from current alignment objectives, creating an Alignment–Reality Gap that is difficult to audit or correct. Existing remediation typically requires re-annotation under revised guidelines, which introduces systematic challenges, including guideline ambiguity, annotator interpretation drift, and reduced consistency at scale. We introduce TRACE (Triage and Re-align by Alignment Conflict Evaluation), a framework that transforms re-alignment into a structured optimization problem over existing data without requiring fresh human annotation. Leveraging a stronger model as a proxy judge, TRACE operates via a three-stage pipeline: (1) triaging preference pairs into inversion, suppression, or retention categories based on alignment conflicts; (2) computing an alignment impact score via bi-level optimization to prioritize high-leverage samples; and (3) executing updates using a hybrid objective that combines relational losses (e.g., IPO) for preference inversion and punitive losses (e.g., NPO) for response suppression. Experiments on Qwen2.5-7B, Gemma-2-9B, and Llama-3.1-8B demonstrate robust re-alignment on synthetic benchmarks and the PKU-SafeRLHF dataset without degrading general utility. This work provides a scalable approach for LLM realignment under evolving data annotation policies and alignment guidelines. We release our code \href{https://respailab.github.io/TRACE/}{here}.

ICML 2026

Learning Sparse Visual Representations via Spatial-Semantic Factorization

Theodore Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel C Codella, Tristan Naumann, Hoifung Poon, Mu Wei

Self-supervised learning (SSL) faces a tension between semantic understanding and image reconstruction. High-level semantic SSL methods such as DINO encourage transformation-invariant global representations for augmentation alignment, while reconstruction-oriented methods such as MAE preserve dense feature grids for spatial grounding but often yield weaker semantic abstractions. We introduce STELLAR, a framework that alleviates this tension by factorizing visual features into a low-rank product of semantic concepts and their spatial distributions. This disentanglement allows us to perform augmentation alignment on semantic tokens while maintaining spatial localization through a localization matrix for reconstruction. We demonstrate that as few as 16 sparse tokens under this factorized form can simultaneously support high-quality reconstruction (2.60 FID) and strong semantic transfer (79.10% ImageNet accuracy). Our results highlight STELLAR as a versatile sparse representation that bridges discriminative and generative vision by separating semantic identity from spatial geometry. Code is available at https://github.com/microsoft/STELLAR.

ICML 2026

Unbiased and Second-Order-Free Training for High-Dimensional PDEs

Jaemin Seo, Su Rin Lee, Jae Yong Lee

Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not require explicit Hessian evaluations. It has recently been established that the commonly used Euler–Maruyama (EM) time discretization induces an intrinsic bias in BSDE training losses. While high-order schemes such as Heun can fully eliminate this bias, such schemes re-introduce second-order spatial derivatives and incur substantial computational overhead. In this work, we provide a principled analysis of EM-induced loss bias and propose an unbiased, second-order-free training framework that preserves the computational advantages of BSDE methods. Our code is available at https://github.com/seojaemin22/Un-EM-BSDE.

ICML 2026

More Capable, Less Cooperative? When LLMs Fail at Zero-Cost Collaboration

Advait Yadav, Sidney Black, Oliver Sourbut

Large language model (LLM) agents increasingly coordinate in multi-agent systems, yet we lack an understanding of where and why cooperation fails. Many real-world coordination problems are not social dilemmas: helping others—sharing documentation, unblocking a teammate—costs the helper almost nothing while producing substantial collective benefit. Whether LLM agents cooperate in this regime, where helping is free and they are explicitly instructed to do so, remains unknown. We build a turn-based multi-agent environment that strips away all strategic complexity, making cooperation costless and trivially optimal. Across eight widely used LLMs, capability does not predict cooperation: OpenAI o3 reaches only 17\% of optimal collective performance while the weaker o3-mini reaches 50\%, despite identical instructions to maximize group revenue. Using a causal decomposition that automates one side of agent communication, we separate cooperation failures from competence failures, and find that several capable models actively withhold information despite gaining nothing from withholding. Targeted interventions address each mode: explicit protocols roughly double the performance of competence-limited models, while small sharing incentives unlock cooperation-limited ones. Our results suggest that scaling intelligence alone will not solve coordination in multi-agent systems, and will require deliberate cooperative design, even when helping costs nothing.

ICML 2026

Steering Large Language Models through the DMTA Cycle: Structure-Based Drug Design via Knowledge-Driven Bi-Level Thompson Sampling

Xuanning Hu, Hao Tuo, Jinglong Ji, Anchen Li, Qianli Xing, Bo Yang

Structure-based drug design (SBDD) can be effectively realized through an iterative refinement via the Design-Make-Test-Analyze (DMTA) cycle, which is a common workflow used by human experts. However, most conventional deep learning-based models as one-shot generators that lack feedback mechanisms, leaving the DMTA loop disconnected. In this work, we propose K-BTS, a Knowledge-Driven Bi-level Thompson Sampling framework that formalizes iterative SBDD as a Dynamic Hierarchical Multi-Armed Bandit problem. K-BTS closes the DMTA loop by decoupling decisions into two levels: an upper-level policy that prioritizes high-potential molecular lineages and a lower-level mechanism that retrieves explicit chemical rules to guide LLM generation. By integrating a dual-level Bayesian update, the framework transforms sparse docking scores into reusable experience. On the CrossDocked2020 benchmark, K-BTS achieves a state-of-the-art Top-1 average docking score. The results from diverse dimensions show that K-BTS ensures search determinism through a smooth, monotonic convergence that synchronizes structural drift with affinity improvement.

ICML 2026

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

Kaiyu Huang, Xingyu Wang, Mingze Kong, Zhubo Shi, Yuqian Hou, Hong Xu, Zhongxiang Dai, Minchen Yu, Qingjiang Shi

In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing approaches tackle this trade-off along two largely independent dimensions: model routing, which switches among models of different scales to match request complexity, and test-time scaling (TTS), which adjusts inference-time compute within a fixed model for fine-grained control. However, this decoupled design introduces inherent limitations. Model routing yields coarse-grained, discrete performance changes due to the sparse set of model scales, while single-model TTS often encounters capacity ceilings and exhibits diminishing returns as compute increases. Moreover, treating the two mechanisms separately restricts adaptability in dynamic inference environments. To overcome these limitations, we introduce *Unified Inference Scaling (UIS)*, which unifies model routing and TTS in a single optimization space. Building on this formulation, we propose UniScale, an online framework that models adaptive UIS as a contextual multi-armed bandit problem and learns inference policies via LinUCB. The framework incorporates efficiency-aware learning and cost modeling to ensure stable and scalable optimization over high-dimensional action spaces. Evaluation shows that UniScale effectively exploits the synergy in the UIS space to deliver a fine-grained and consistently better quality–cost trade-off across diverse, dynamic inference scenarios.

ICML 2026

Chunk-Guided Q-Learning

Gwanwoo Song, Kwanyoung Park, Youngwoon Lee

In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can introduce suboptimality by restricting the policy class to open-loop action sequences. To resolve this trade-off, we present Chunk-Guided Q-Learning (CGQ), a single-step TD algorithm that guides a fine-grained single-step critic by regularizing it toward a chunk-based critic trained using temporally extended backups. This reduces compounding error while preserving fine-grained value propagation. We theoretically show that CGQ attains tighter critic optimality bounds than either single-step or action-chunked TD learning alone. Empirically, CGQ achieves strong performance on challenging long-horizon OGBench tasks, often outperforming both single-step and action-chunked methods.

ICML 2026

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

Yonggan Fu, Lexington Whalen, Zhifan Ye, Xin Dong, Shizhe Diao, Jingyu Liu, Chengyue Wu, Hao Zhang, Enze Xie, Song Han, Maksim Khadkevich, Jan Kautz, Yingyan Celine Lin, Pavlo Molchanov

Diffusion language models (dLMs) have emerged as a promising paradigm enabling parallel generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To this end, we study AR-to-dLM conversion, which transforms pretrained AR models into efficient dLMs that excel in speed while preserving AR models’ task accuracy. We achieve this by identifying limitations in the attention patterns and objectives of existing AR-to-dLM methods and then proposing methodologies and actionable insights for scalable AR-to-dLM conversion. Specifically, we first systematically compare different attention patterns and find that maintaining pretrained AR weight distributions is key to effective AR-to-dLM conversion. Accordingly, we introduce a continuous pretraining scheme with a block-wise attention pattern. We find that, in addition to block-wise attention’s known benefit of enabling KV caching, its block-wise causality better preserves pretrained AR models’ weight distributions, leading to a win–win in accuracy and efficiency. Second, to mitigate the training–test gap in mask token distributions (uniform vs. highly left-to-right), we propose a position-dependent token masking strategy that assigns higher masking probabilities to later tokens during training to better mimic test-time behavior. These studies lead to the Efficient-DLM model family, which outperforms state-of-the-art AR models and dLMs in accuracy–throughput trade-offs; for example, our Efficient-DLM-8B achieves +5.4\%/+2.7\% higher accuracy with 4.7$\times$/2.8$\times$ higher throughput compared to Dream-7B and Qwen3-4B, respectively.

ICML 2026

PortraitRL: Reinforcement Learning for Personalized Portrait Pose Transfer with Multi-Objective Reward Modeling

Jiahui Wu, Zelong Sun, Yanbiao Ma, Zhiwu Lu

Portrait pose transfer (PPT) requires generative models to preserve fine-grained identity details while following complex pose and layout modification instructions. Existing methods often struggle with extensive data annotation requirements or employ optimization objectives that are suboptimal for addressing PPT's two key challenges. In this work, we propose PortraitRL, a novel post-training framework that addresses these challenges with a multi-objective reward mechanism. Specifically, we employ LVLM-based reward functions to effectively evaluate PPT's two challenges and apply within-group standardization to eliminate scale differences, allowing these rewards to effectively guide optimization. More importantly, we devise a novel reinforcement learning algorithm, Negative-aware Score Preference Optimization (NaSPO), which automatically identifies positive and negative preference samples through within-group advantages, eliminating annotation requirements while fully leveraging both positive and negative learning signals. Extensive experiments show state-of-the-art performance, with significant improvements in both detail preservation and editing accuracy.

ICML 2026

AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs

WenXiang Lin, Juntao Huang, LuHan Zhang, Laiyi Li, Xiang Bao, mengyang zhang, Bing Wang, Shaohuai Shi

Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-bit gradients, which would easily cause slow convergence or accuracy loss. To address this, we introduce AGoQ, incorporating two new techniques: 1) a layer-aware activation quantization algorithm that allocates appropriate bit-widths for activations of various layers based on their types and pipeline stages to achieve near 4-bit activation storage, and 2) a gradient quantization algorithm that reduces memory usage and shortens communication time by employing 8-bit gradient storage and precision-preserving 8-bit All-Reduce communication. We conduct extensive experiments using different sizes of LLMs on two GPU clusters (up to 64 GPUs), and the experimental results show that our AGoQ reduces the memory by up to 52\% and achieves up to 1.34$\times$ improvement of training speed compared to state-of-the-art training systems Megatron-LM (w/ or w/o ZeRO), COAT and DeepSpeed with 8B to 32B LLaMA models, while achieving convergence loss on pretraining and comparable accuracy on downstream tasks with LLaMA architectures.

ICML 2026

LLM-Guided Loop Bound Generation for Program Termination Verification

Zan Gong, Biting Huang, Fei He

Program termination is a fundamental liveness property in software verification. Proving termination of a given program is a formidable challenge due to the undecidability of the problem. In this paper, we propose LIFT, a termination verification framework that leverages LLMs to generate loop bounds within a guess-and-check workflow. LIFT couples this generation with a sound formal validation procedure that both guarantees all reported terminations and refutes invalid loop bounds via violation analysis. Experiments on publicly accessible termination benchmarks show that LIFT significantly outperforms existing termination verification tools.

ICML 2026

Selling Data as a Digital Good with Scaling Valuations

Ningyuan Li, Yanru Guan, Xiaotie Deng, Zihe Wang, Jie Zhang

We study mechanism design for selling data as a digital good when the value derived from training AI models follows a scaling law. The seller faces a linear cost when producing data, while the buyers benefit from additional data with diminishing returns as data volume increases. This departs from classical auction models by allowing allocations to be continuous quantities of data rather than binary outcomes. We first analyze an offline setting in which all buyer types are realized simultaneously, characterizing profit-optimal mechanisms and showing how virtual-value methods extend to continuous data allocations. We then consider an online setting with sequential arrivals, where production decisions must be made under demand uncertainty. We show that myopic allocation and fixed production plans can be arbitrarily suboptimal, whereas a simple two-stage algorithm that combines upfront production with adaptive expansion achieves a constant-factor approximation to the offline optimum. Finally, we study bilateral data trading under asymmetric information, where both the buyer’s value and the seller’s cost are private. Although the optimal truthful mechanism has a complex structure, we show that simple and implementable mechanisms recover a constant fraction of the first-best gain-from-trade. Overall, our results highlight how scaling laws introduce new algorithmic trade-offs in market design and provide performance guarantees for data markets under uncertainty.

ICML 2026

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

Xiongwei Zhu, Xiaojian Liao, Tianyang Jiang, Yusen Zhang, Liang Wang, Limin Xiao

Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining high model capacity. However, in memory-constrained inference scenarios, only a small set of experts can be cached. Experts not in the cache must be fetched from slow external storage (e.g., UFS), leading to frequent evictions and substantial I/O overhead. We propose ReMoE, a router fine-tuning framework designed to boost token-wise expert reuse. ReMoE biases the router toward recently selected experts, producing temporally stable routing that better matches cache locality constraints. By increasing short-horizon expert reuse, ReMoE reduces expert fetches from storage without adding inference-time computation. Experiments on DeepSeek and Qwen models show that ReMoE improves expert reuse by 26\% while maintaining downstream task performance. Real-system evaluations further confirm these benefits, improving output throughput by 8.4\% under vLLM GPU--CPU expert offloading and reducing TPOT by 43.6-49.8\% under llama.cpp on Jetson Orin NX, corresponding to a 1.77-1.99$\times$ decode speedup across diverse workloads. Checkpoints and usage instructions are available at https://github.com/BUAA-OSCAR/ReMoE.

ICML 2026

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

Jung Hyun Lee, June Yong Yang, Jungwook Choi, Eunho Yang

As large language models continue to scale, low-bit weight-only post-training quantization (PTQ) offers a practical solution to their memory-efficient deployment. Although block-wise PTQ is capable of matching the full-precision (FP) baseline on basic language modeling and understanding, its quality is degraded for \textit{generative} tasks---especially at longer responses and extended chains of thought, which is critical in boosting task accuracy. We attribute this shortfall to two factors: (i) the omission of the unembedding layer (the LM head) in block-wise optimization and (ii) the reliance on the mean squared error (MSE) objective. Both factors cause the token probability distribution of the quantized model to misalign with that of the FP model, yielding notable accuracy drops on text generation benchmarks. To rectify the discrepancy, we introduce \emph{Logit-aware Final-block Quantization (LFQ)}, a simple yet effective enhancement to block-wise PTQ that quantizes the final Transformer block by minimizing the cross-entropy between the logits of the FP model and those of its quantized counterpart. By aligning token probabilities at the logit level in the final block, LFQ consistently improves the accuracy of complex generation tasks over state-of-the-art block-wise PTQ across diverse model families, while maintaining parity with FP baselines on language modeling and understanding.

ICML 2026

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

Wendao Wu, Fangqing Zhang, Haihan Zhang, Cong Fang

Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization. While existing studies offer isolated insights, a unified theoretical framework explaining the efficacy of KT across these disparate regimes remains lacking. In this work, we establish a unified spectral analysis of SGD dynamics in high-dimensional linear regression, elucidating the efficiency of KT across seemingly disparate regimes. We characterize KT efficiency through two distinct mechanisms: \emph{Spectral Horizon Expansion} in KD, which enables the capture of statistically inaccessible high-frequency signals, and \emph{Spectral Denoising} in W2S, where the student acts as a filter for optimization noise. Our framework unifies these phenomena, revealing that the efficacy of transfer is governed by the interplay between implicit regularization and heterogeneous spectral learning speeds over the spectrum.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.