ICML 2025 Honorable Mentions: Honesty, Video Generation, and LLM Memory
icmlconf · x · 2026-07-06
ICML 2025 announced the first batch of Outstanding Paper Honorable Mentions, featuring three papers across different domains: "The Obfuscation Atlas" uses deception probes to reveal the emergence of honesty during RLVR training; "Motion Attribution for Video Generation" analyzes the sources of motion components in video generation models; and "How much can language models memorize?" systematically evaluates the memory capacity boundaries of large models.
Related event: ICML 2025 Announces Outstanding Paper Honorable Mentions(4 posts)→
More from Research
- Deep Learning Course Adds Mechanistic Interpretability Lecture This Winter — CSProfKGD · 2026-10-26
- INCLUDE-2.0 benchmark evaluates regional knowledge across 91 languages and 86 countries — ABosselut · 2026-10-26
- CoRL paper: flow-matching VLAs can run 1-step Euler inference with no retraining — kaixhin · 2026-10-26
- CoVer at EMNLP 2026: Training Code LLMs to Generate and Self-Verify Simultaneously — algo_diver · 2026-10-26
- Robotic dexterity should be judged on speed, force control and tool use, not copying humans — DJiafei · 2026-10-26
- Turing-complete malware can run in PyTorch's backward pass via a zero-valued loss — retr0jirachi · 2026-10-26