[ICML2026] The first, fully verified, sorry-free, large-scale Lean 4 library for statistical learning theory, covering infrastructures for mordern statistics and learning theory.

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

[ICML 2026] Official PyTorch implementation of From Observations to States: Latent Time Series Forecasting

[ICML 2026] Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

[ICML 2026] Activation with Intrinsic-Extrinsic Consensus

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas

Source code for the ICML 2026 paper "Rethinking Contrastive Learning in Graph Collaborative Filtering: Limitations and A Simple Remedy"

[ICML 2026] Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

Official implementation of the ICML 2026 paper "Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model".

[ICML 2026] FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection

Curated list of ICML 2026 papers on decentralized/distributed training & serving of LLMs

Reproducibility minimal release — Moral Orientation and Calibration (ICML 2026 Pluralistic Alignment Workshop)

Inference-time LLM structured pruning via probe-based representation-parameter coupling (ICML 2026)

Official repository for the ICML 2026 paper “Learning to Emulate Chaos: Adversarial Optimal Transport Regularization.”

(ICML 2026) ALSO: Adversarial Online Strategy Optimization for Social Agents — first online, adversarial-bandit framework for strategy optimization in non-stationary multi-agent social simulation.