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
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11