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

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

Xiang Li, Dianbo Liu, Kenji Kawaguchi

Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse. Existing strategies for enhancing diversity predominantly focus on intervening during the generation trajectory. We identify a critical oversight that the standard Gaussian initialization often causes trajectories to collapse into dominant modes because it is agnostic to the guidance potential landscape. In this work, we formulate selecting the initial noise from a *guidance potential posterior*, which effectively re-weights the prior towards diversity-rich regions. To sample from this distribution efficiently, we introduce *Diversity-inducing Initialization* (DivIn), which leverages Langevin dynamics to actively navigate the initialization landscape, steering initial noise away from collapsing regions while anchoring them to the valid data manifold. Our method serves as an inference-time diversity enhancement compatible with both diffusion and flow matching models. Extensive experiments show that DivIn exhibits a superior performance in both class-to-image and text-to-image scenarios. Furthermore, we highlight that as DivIn is orthogonal to trajectory-based methods, combining them significantly expands the diversity-quality Pareto frontier beyond what either achieves in isolation.

ICML 2026

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

Liyan Chen, Yael Tauman Kalai, Zoe Xi

As AI models continue to develop powerful capabilities, it becomes critical that we are able to verify that their output is aligned with our intentions. A recent line of work focuses on verification via debate, a model of interactive proofs where two competing powerful provers, or AI models, debate each other to convince a weak verifier, or a human, of the correctness of their claim. However, debate assumes that the two AI models possess equal abilities and that one of them is truthful, which may not be realistic. In this work, we show *how to avoid debate*: we initiate the study of *single-prover* interactive proofs for AI safety. Prior results in single-prover interactive proofs do not immediately carry over to the AI safety setting because they do not work when the computation has access to an oracle, such as to human judgment or an external database such as the web. We present doubly-efficient single-prover interactive proofs for oracle-aided computations (also known as relativizing proofs), in the settings where (1) the computation is robust, in the sense that the output does not change if at most a small fraction of the answers to oracle queries are incorrect, or (2) the oracle is a low-degree polynomial. These results suggest that interactive verification is possible even without debate, under structured or noise-tolerant oracle access.

ICML 2026

What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity

Haoxi Li, Qinglin Hou, Jianfei Ma, Jinxiang Lai, Tao Han, Sikai Bai, Jingcai Guo, Jie Zhang, Song Guo

To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities directly into their policies via explicit CoT reasoning with reinforcement learning (RL). However, mere passive exploitation of reasoning on visited states is insufficient for sparse-reward agentic tasks, as it lacks the epistemic drive to actively uncover the *known unknown* required for robust generalization. We ask: *Can VLM agents actively find signals that challenge and update their internal world model through curiosity-driven exploration?* In this work, we propose **GLANCE**, a unified framework that bridges reasoning and exploration by grounding the agent's linguistic world model into the stable visual representations of an evolving target network. Crucially, **GLANCE** leverages the discrepancy between linguistic prediction and visual reality as an intrinsic curiosity signal within reinforcement learning, steering the agent to actively explore areas where its internal model is uncertain. Extensive experiments across a series of agentic tasks show the effectiveness of **GLANCE**, and demonstrate that aligning *what the agent thinks* with *what the agent sees* is key to solving complex or sparse agentic tasks.

ICML 2026

Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents

Jian Li, Hua Huang

While Large Language Models (LLMs) possess strong reasoning capabilities, enabling them to learn continuously from experience without parametric retraining remains an open challenge. Existing Retrieval-Augmented Generation (RAG) approaches typically treat memory as a static or append-only corpus, leading to "memory saturation," where accumulating noise and redundant information degrade performance over time. To address this, we propose an Experience Library Optimization framework that treats the agent's external memory, which we call the experience library, as a learnable parameter under an explicit capacity budget. We introduce Textual Stochastic Gradient Descent (TSGD), a discrete optimization algorithm that refines this library via failure-driven Add, Edit, and Delete operations. TSGD estimates "textual gradients" through self-reflection and uses a dual-verification mechanism to ensure generalization, which prevents overfitting to local errors. Empirical results on MATH and AIME benchmarks show that TSGD achieves state-of-the-art performance, improving accuracy by up to $18.7\%$ over zero-shot baselines and substantially outperforming static RAG, while keeping a compact memory footprint (compressing hundreds of experiences into $\approx 30$ high-utility rules).

ICML 2026

LILO: Bayesian Optimization with Natural Language Feedback

Kasia Kobalczyk, Zhiyuan Jerry Lin, Benjamin Letham, Zhuokai Zhao, Maximilian Balandat, Eytan Bakshy

Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form objectives. In response, we introduce Language-in-the-Loop Optimization (LILO), a Bayesian optimization (BO) framework that employs a large language model (LLM) to translate free-form natural language feedback and prior knowledge from a decision maker into structured preference signals, going beyond the restrictive scalar or pairwise feedback formats typically assumed in preferential BO. The LLM-derived preferences are integrated by a Gaussian process proxy model, enabling principled acquisition-driven exploration with calibrated uncertainty. By placing the LLM in a supporting role rather than as the optimizer itself, LILO preserves the sample efficiency and stability of BO while providing a flexible and expressive feedback interface. Across synthetic and real-world benchmarks, LILO consistently outperforms both conventional preference-based BO methods and LLM-only optimizers, with particularly strong gains in feedback-limited regimes. The code for reproducing our experimental results is available at: https://github.com/facebookresearch/lilo.

ICML 2026

Intervene When It Doubts: Conjunction-Guided Interactive Reasoning

Qianyue Wang, Jinwu Hu, Yaofo Chen, Yufeng Wang, Bailin Chen, Huanxiang Lin, Yu Rong, Yuanqing Li, Zhiquan Wen, Mingkui Tan

Large Reasoning Models (LRMs) excel at complex reasoning but suffer from inefficient reasoning, like overthinking and overshoot. These issues stem from excessive or misdirected reasoning triggered by the model's "doubt", manifested as self-validation and exploratory extension, increasing computational cost and degrading performance. Existing efficient reasoning methods seek to regulate reasoning via internal signals or static schedules, lacking specialization in the "doubt" characteristics of LRMs. To address this, we propose a Conjunction-Guided Intervention (CGI) reasoning framework that intervenes when the model shows signs of doubt. Our key insight is that overthinking and overshoot in LRMs arise from conjunction-triggered extensions where LRMs exhibit "doubt" through transitional conjunctions, extending redundant self-validation and exploration without timely state-based correction. Building on this insight, CGI pauses reasoning at conjunction markers of doubt for external state-based feedback, adaptively extending or terminating reasoning to reduce redundancy while preserving accuracy. The feedback is generated via criteria evaluation (rationality and completeness) and comes from either human or LLM proxies. We train the target model by Group Relative Policy Optimization (GRPO) to adapt to the interactive mode. Experiments show that our framework achieves a superior balance between accuracy and reasoning length.

ICML 2026

Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning

Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen

The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Stochastic Combinatorial Optimization (SSCO) particularly challenging for reinforcement learning. Hierarchical Reinforcement Learning (HRL) offers a natural decomposition, but it places the high-level policy in a Semi-Markov Decision Process (SMDP) where actions have variable durations, making it difficult to learn a world model that is suitable for planning. We introduce a model-based hierarchical framework for sequential stochastic combinatorial decision-making that directly addresses this issue. Our method combines a latent-space tree-search planner with an SMDP-aware world model for variable-duration decisions. A multi-timescale objective structures the latent dynamics so that transition magnitudes reflect the effective temporal scales of abstract actions, enabling efficient lookahead under adaptive temporal abstraction. We further learn a subgoal-conditioned budget policy jointly with the world model to support context-aware resource allocation. Across challenging SSCO benchmarks, our method outperforms strong baselines.

ICML 2026

Generative Large Neighborhood Search: Scalable Set Cover Optimization via Discrete Diffusion

Achref Jaziri, Thibaut Cuvelier, Bruno Adrien De Backer

Large-scale Set Cover Problems (SCP) with millions of variables and complex cost structures require high-quality solutions within seconds, yet remain beyond the reach of exact solvers and pose severe generalization challenges for neural methods. Such problems necessitate decomposition into bounded subproblems; however, when the induced subproblem topology differs from that observed during training, existing neural approaches often fail to transfer reliably. We introduce Generative Large Neighborhood Search (GLNS), which reframes neighborhood selection as generation using a discrete diffusion model. Our key insight is that the diffusion denoising trajectory exposes variables exhibiting high prediction instability across timesteps and identifies regions where local repair yields downstream improvement. GLNS exploits this trajectory-level signal to construct high-impact neighborhoods via a localized, bounded-complexity generative sampling procedure, enabling robust neighborhood selection without retraining. As a result, GLNS transfers effectively across cost regimes and instance scales within SCP. Under tight and equal wall-clock budgets, GLNS consistently outperforms established neural baselines and achieves competitive performance with state-of-the-art MIP solvers. These results demonstrate trajectory-guided generation as a scalable framework for large-scale SCP and suggest potential relevance to other constrained optimization settings.

ICML 2026

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Menglin Xia, Xuchao Zhang, Shantanu Dixit, Paramaguru Harimurugan, Rujia Wang, Victor Rühle, Robert Sim, Chetan Bansal, Saravan Rajmohan

Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective reasoning. We introduce Memora, a harmonic memory representation that structurally balances abstraction and specificity. Memora organizes information via its *primary abstractions* that index concrete memory values and consolidate related updates into unified memory entries, while *cue anchors* expand retrieval access across diverse aspects of the memory and connect related memories. Building on this structure, we employ a retrieval policy that actively exploits these memory connections to retrieve relevant information beyond direct semantic similarity. Theoretically, we show that standard Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG)-based memory systems emerge as special cases of our framework. Empirically, Memora establishes a new state-of-the-art on the LoCoMo and LongMemEval benchmarks, demonstrating better retrieval relevance and reasoning effectiveness as memory scales.

ICML 2026

MAMBO-G: Magnitude-Aware Mitigation for Boosted Guidance

Shangwen Zhu, Qianyu Peng, Zhilei Shu, Yuting Hu, Han Zhang, Andy Zheng, Xinyu Cui, Jian Zhao, Ruili Feng, Fan Cheng

High-fidelity text-to-image and text-to-video generation typically relies on Classifier-Free Guidance (CFG), but achieving optimal results often demands computationally expensive sampling schedules. In this work, we propose MAMBO-G, a training-free acceleration framework that significantly reduces computational cost by dynamically optimizing guidance magnitudes. We observe that standard CFG schedules are inefficient, applying disproportionately large updates in early steps that hinder convergence speed. MAMBO-G mitigates this by modulating the guidance scale based on the update-to-prediction magnitude ratio, effectively stabilizing the trajectory and enabling rapid convergence. This efficiency is particularly vital for resource-intensive tasks like video generation. Our method serves as a universal plug-and-play accelerator, achieving up to 3$\times$ speedup on Stable Diffusion v3.5 (SD3.5) and 4$\times$ on Lumina. Most notably, MAMBO-G accelerates the 14B-parameter Wan2.1 video model by 2$\times$ while preserving visual fidelity, offering a practical solution for efficient large-scale video synthesis. Our implementation follows a mainstream open-source diffusion framework and is plug-and-play with existing pipelines.

ICML 2026

Stop When Further Reasoning Won’t Help: Attention-State Adaptive Generation in Reasoning Models

Jiakai Li, Ke Qin, Rongzheng Wang, Yizhuo Ma, Qizhi Chen, Muquan Li, Shuang Liang

By incorporating test-time compute scaling, large reasoning models (LRMs) can solve complex problems through explicit chain-of-thought (CoT) reasoning processes. However, they often suffer from overthinking, resulting in redundant token outputs and degraded accuracy. Current methods to mitigate this issue remain limited: training-based approaches require substantial computational resources, while training-free methods rely on well-crafted prompts or unreliable confidence signals. In this work, we investigate early stopping from the perspective of attention distributions and propose a simple method, ASAG, which infers the model's reasoning state and adaptively adjusts the generation strategy. The proposed framework is training-free and plug-and-play, enabling seamless integration into existing LRMs. Extensive experiments on nine benchmarks demonstrate consistent improvements across mainstream LRMs with varying parameter scales, including the DeepSeek-R1-Distill and Qwen3 series. Specifically, ASAG improves average accuracy by 3.2% while reducing the number of generated tokens by nearly 40% across all reasoning tasks on Qwen3-8B.

ICML 2026

VeRO: A Harness for Agents to Optimize Agents

Varun Ursekar, Apaar Shanker, Veronica Chatrath, Yuan Xue, Samuel Marc Denton

An important emerging application of coding agents is *agent harness optimization*: the iterative improvement of a *target agent* by editing and evaluating its code. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Harness optimization differs from conventional software engineering: agent harnesses interleave deterministic code with stochastic LLM completions, requiring structured capture of both intermediate execution traces and downstream outcomes. To address these challenges, we introduce (1) VeRO (Versioning, Rewards, and Observations), an *outer harness* that provides versioned snapshots, budget-controlled evaluation, and structured execution traces of *target harnesses*, and (2) VeRO-Bench, a benchmark suite of target agents and tasks with reference evaluation procedures. Using VeRO, we conduct an empirical study comparing optimizers across tasks and analyzing which modifications reliably improve target agent harnesses. We release VeRO to support research on agent optimization as a core capability for coding agents. Code is available at https://github.com/scaleapi/vero.

ICML 2026

Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities

Florian Dietz, William Wale, Oscar Gilg, Robert McCarthy, Felix Michalak, Gustavo Ewbank Rodrigues Danon, Miguelito de Guzman, Dietrich Klakow

Detecting misalignment in large language models is challenging because models may learn to conceal misbehavior during training. Standard auditing techniques fall short: black-box methods often cannot distinguish misaligned outputs from benign ones, and mechanistic interpretability does not scale with model capabilities. We introduce Split Personality Training (SPT), which fine-tunes a second ``honest persona'' into LoRA parameters that remain inactive during normal operation. After the main model responds, we activate the LoRA adapter and insert a trigger string, enabling the honest persona to review the response while accessing the main model's latent states. We test our method on the Anthropic Auditing Game Model Organism, a benchmark where Llama-3.3-70B is trained to exploit reward hacks while concealing this behavior. SPT achieves 96% overall accuracy, whereas Anthropic reports near 0% accuracy. The honest persona reveals latent knowledge inaccessible to external observers, such as the fictional biases the compromised model was trained on.

ICML 2026

Generalized Discrete Diffusion with Self-Correction

Linxuan Wang, Ziyi Wang, Yikun Bai, Wei Deng, Guang Lin, Qifan Song

Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and hinders practical performance. In this work, we propose a **S**elf-**C**orrecting **D**iscrete **D**iffusion (SCDD) model to reformulate pretrained self-correction with explicit state transitions and learn directly in discrete time. Our framework also simplifies the training noise schedule, eliminates a redundant remasking step, and relies exclusively on uniform transitions to learn self-correction. Experiments at the GPT-2 scale demonstrate that our method enables more efficient parallel decoding while preserving generation quality. Our code is available at https://github.com/laaaarrywang/Self-Correcting-Discrete-Diffusion.git.

ICML 2026

Persistent Semantic Entities in Tool-Augmented LLM Systems

Zhaohui Geoffrey Wang

Tool-augmented LLM agents can harbor implicit state that persists across sessions, activates through events, and propagates across agent boundaries—all invisible to standard debugging. We formalize this as Persistent Semantic Entities (PSE): constructs defined by name binding, event triggering, and cross-boundary propagation, and evaluate them across 20 models from 9 families (3B–671B parameters). First, all tested models are susceptible to contamination (20–100%), with name binding as the dominant mechanism: without it, contamination is 0%. Second, persistence depends on contamination type rather than scale or deployment—factual injection conflicting with parametric knowledge self-corrects, but preference, persona, and instruction contamination persists at 100% over a 10-turn horizon with no decay, an effect that holds across providers in our controlled setting and is consistent with a model-intrinsic explanation. Third, context-isolated self-verification achieves 20–79% reduction without oracle references while keyword-based detection produces systematic false positives, and contamination compounds 3× across multi-agent pipelines. Preference and instruction contamination—persistent, lacking self-correction, and invisible to standard monitoring—represents a particularly concerning attack surface for deployed agent systems.

ICML 2026

Rays as Pixels: Learning A Joint Distribution of Video and Camera Trajectories

Wonbong Jang, Shikun Liu, Soubhik Sanyal, Juan Camilo Perez, Kam Woh Ng, Sanskar Agrawal, Juan-Manuel Perez-Rua, Yiannis Douratsos, Tao Xiang

Can we bridge the gap between perceiving camera trajectories and rendering novel views within a single generative framework? Recovering camera parameters from images and rendering scenes from novel viewpoints are considered the forward and inverse problems in the field of computer vision and graphics. Previous approaches treat these problems in isolation, often failing when image coverage is sparse or camera poses are ambiguous. In this work, we propose Rays as Pixels, a specialized Video Diffusion Model (VDM) that learns a joint distribution of videos and camera trajectories. We represent cameras as dense ray pixels (raxels) and simultaneously denoise them alongside video frames using a novel Decoupled Self-Cross Attention. This joint formulation enables us to: i) generate a video from multiple input images following a defined camera trajectory, ii) perform novel view synthesis from sparse views (without necessarily requiring camera poses), and iii) predict the camera trajectory from a raw video. We evaluate our model on pose estimation, camera-controlled video generation and validate its self-consistency. Please reference supplementary material for more qualitative results.

ICML 2026

NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating

Zhongju Yuan, Geraint A. Wiggins, Dick B.M. Botteldooren

Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free NeuroAuditory Attentive Cognitive Architecture that reframes attention allocation as an auditory salience filtering problem. At its core is OWM, a neuro-inspired Oscillatory Working Memory that maintains stable attractor-like states and triggers higher-cognition ALM processing only when adaptive energy fluctuations signal perceptual salience, triggering higher-level reasoning. On XD-Violence, NAACA improves AudioQwen’s average precision (AP) from 53.50\% to 70.60\% while reducing unnecessary ALM invocations. Furthermore, qualitative case studies on the Urban Soundscapes of the World (USoW) dataset show that OWM captures novel events and subcategory shifts while remaining robust to transient pauses and ambient urban noise.

ICML 2026

A KL-regularization framework for learning to plan with adaptive priors

Alvaro Serra-Gomez, Daniel Jarne Ornia, Dhruva Tirumala, Thomas M. Moerland

Effective exploration remains a key challenge in model-based reinforcement learning (MBRL), especially in high-dimensional continuous control tasks where sample efficiency is critical. Recent work addresses this by using learned policies as proposal distributions for Model-Predictive Path Integral (MPPI) planning. Early approaches update the sampling policy independently of the planner, typically via deterministic policy gradients with entropy regularization. However, since the data distribution is induced by the MPPI planner, misalignment between the policy and planner degrades value estimation and long-term performance. To address this, recent methods explicitly align the policy with the planner by minimizing KL divergence to the planner distribution or by incorporating planner-guided regularization. In this work, we unify these approaches under the Policy Optimization–Model Predictive Control (PO-MPC) framework, a family of KL-regularized MBRL methods that treat the planner’s action distribution as a prior in policy optimization. We show how existing methods emerge as special cases of this family and explore previously unstudied variants. Experiments demonstrate that these variants yield significant performance gains, advancing the state of the art in MPPI-based RL.

ICML 2026

LangPrecip: Language-Aware Multimodal Precipitation Nowcasting

Xudong Ling, chaorong li, Tianxi Huang, Qian Dong, Guiduo Duan

Short-term precipitation nowcasting is inherently under-constrained due to limited historical observation windows: identical observations can lead to multiple plausible future trajectories, especially for extreme events. Existing generative methods rely solely on visual features and lack explicit constraints on precipitation motion semantics, resulting in ambiguous dynamics, blurred details, and unstable predictions. We propose LangPrecip, the first language-guided precipitation nowcasting framework, and contribute LangPrecip-160K, a large-scale radar-text paired dataset with 160K annotated sequences. LangPrecip addresses the under-constrained challenge by leveraging natural-language motion descriptions as explicit semantic constraints to reduce motion ambiguity and introducing a dual-path wavelet consistency unfolding decoder that enforces physical data fidelity during latent-to-pixel reconstruction. By reformulating nowcasting as semantically constrained trajectory generation under the Rectified Flow paradigm with model-based decoder optimization, LangPrecip produces sharper and more physically consistent forecasts. Experiments on Swedish and MRMS benchmarks demonstrate substantial improvements over state-of-the-art vision-only methods, achieving over 60\% and 19\% relative gains in heavy-rainfall CSI at 80-minute lead time with enhanced spatial detail preservation. Dataset is available at https://github.com/UESTC-LXD/LangPrecip.

ICML 2026

WorldCompass: Reinforcement Learning for Long-Horizon World Models

Zehan Wang, Tengfei Wang, Haiyu Zhang, Xuhui Zuo, Junta Wu, Haoyuan Wang, Wenqiang Sun, Zhenwei Wang, Chenjie Cao, Hengshuang Zhao, Chunchao Guo, Zhou Zhao

This work presents WorldCompass, a novel Reinforcement Learning (RL) post-training framework for the long-horizon, interactive video-based world models, enabling them to explore the world more accurately and consistently based on interaction signals. To effectively "steer" the world model's exploration, we introduce three core innovations tailored to the autoregressive video generation paradigm: 1) Clip-level Roll-out Strategy: We generate and evaluate multiple samples at a single target clip, which significantly boosts roll-out efficiency and provides fine-grained reward signals. 2) Complementary Reward Functions: We design reward function for both interaction-following accuracy and visual quality, which provide direct supervision and effectively suppress reward-hacking behaviors. 3) Efficient RL Algorithm: We employ the negative-aware fine-tuning strategy coupled with various efficiency optimizations to efficiently and effectively enhance model capacity. Evaluations on the SoTA open-source world model, WorldPlay, demonstrate that WorldCompass significantly improves interaction accuracy and visual fidelity across various scenarios.

Keep browsing

More papers from top AI conferences

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