31. Last day of #ICML2026! Catch "Scale Dependent Data Duplication" to close out the conference. Last day of #ICML2026 ! Catch "Scale Dependent Data Duplication" to close out the conference. Jessica Chudnovsky ✈️ ICML 2026 @jchudnov Two papers accepted at the #ICML2026 worksho 07/11 08:48 ♡
32. Verification has emerged as a new scaling axis 🚀 LLM-as-a-Verifier shows that scaling verification... Verification has emerged as a new scaling axis 🚀 LLM-as-a-Verifier shows that scaling verification can push performance to SOTA across Terminal-Bench V2, SWE-Bench Verified 07/10 07:45 ♡
33. Check out TRACE, a new self-improvement approach where the agent identifies the missing capabilities... Check out TRACE, a new self-improvement approach where the agent identifies the missing capabilities behind its own failures and trains itself to address them. TRACE-trained Qwen3. 07/10 07:45 ♡
34. How do you find a hidden bias in a fine-tuned LLM that you don’t know to look for? Amplify it. Dist... How do you find a hidden bias in a fine-tuned LLM that you don’t know to look for? Amplify it. Distill to Detect (D2D) surfaces hidden biases by distilling the shift between a susp 07/10 07:30 ♡
35. Check out this oral presentation today & runner up at the Foundations of Deep Generative Models ... Check out this oral presentation today & runner up at the Foundations of Deep Generative Models workshop! #ICM #ICML2026 ngrats to @jchudnov , @JoshuaK92829 , Noam Levi, @RylanScha 07/10 07:29 ♡
36. Are you at ICML 2026 in Seoul? 🇰🇷 Check out the full list of papers from Stanford AI Lab — spannin... Are you at ICML 2026 in Seoul? 🇰🇷 Check out the full list of papers from Stanford AI Lab — spanning coding agents, LLM reasoning, evaluation & benchmarks, AI safety 07/06 19:07 ♡
37. LLMs are better at predicting what other models will say than what’s actually true. When they’re wro... LLMs are better at predicting what other models will say than what’s actually true. When they’re wrong, they’re wrong together; so polling can’t recover the truth. Check out this p 07/06 01:34 ♡
38. C Congratulations to the team on the #ICML2026 workshop Oral! @jchudnov (co-lead), @JoshuaK92829 (co... Congratulations to the team on the #ICML2026 workshop Oral! @jchudnov (co-lead), @JoshuaK92829 (co-lead), Noam Levi (co-lead), @RylanSchaeffer , @yegordb , Bo He, Mehmet Donmez, @s 07/05 08:20 ♡
39. Deduplication is standard practice but never perfect --this work measures what the residue costs in ... Deduplication is standard practice but never perfect --this work measures what the residue costs in compute-equivalent terms, and shows the worst-case repetition structure is predi 07/05 08:20 ♡
40. What if the way we collect human feedback in robotics is quietly losing information? If one traject... What if the way we collect human feedback in robotics is quietly losing information? If one trajectory drops the cutlery and another drops the plate, asking for a single preference 07/03 02:02 ♡
