Kianté Brantley
@xkianteb
Followers
2K
Following
2K
Media
12
Statuses
3K
Assistant Professor at Harvard | Fitness enthusiast | (He/Him/His)
Joined May 2009
RT @KempnerInst: New in the #DeeperLearningBlog: @GaoZhaolin and collaborators including the #KempnerInstitute's Kianté Brantley presents a….
kempnerinstitute.harvard.edu
Recent LLM advances show the effectiveness of RL with rule-based rewards, but methods like GRPO and PPO are costly due to critics or multiple generations per prompt. We propose a […]
0
5
0
Wow.
Where the first authors come from in #ACL2025 compared to #ACL2024?. The rise of the East and the significant decline of the West!. From the opening slides of @aclmeeting
0
0
1
RT @andre_t_martins: The sparsemax paper reached 1000 citations now and it keeps to bear fruit. Two recent sparse attention examples: long-….
0
4
0
RT @robertarail: I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery!. We’re looking for strong Research Scientists….
0
260
0
RT @MehulDamani2: 🚨New Paper!🚨.We trained reasoning LLMs to reason about what they don't know. o1-style reasoning training improves accura….
0
268
0
RT @jacobandreas: 👉 New preprint! Today, many the biggest challenges in LM post-training aren't just about correctness, but rather consiste….
0
11
0
RT @polynoamial: Today, we at @OpenAI achieved a milestone that many considered years away: gold medal-level performance on the 2025 IMO wi….
0
544
0
RT @kaiwenw_ai: I’m presenting two papers on value-based RL for post-training & reasoning on Friday at @ai4mathworkshop at #ICML2025!.1️⃣ Q….
0
16
0
RT @hankyang94: Sharing a project that’s kept me excited for months:. Five years ago, I tried projecting a 10000×10000 symmetric matrix ont….
0
36
0
RT @yoavartzi: Check out our LMLM, our take on what is now being called a "cognitive core" (as far as branding go, this one is not bad) can….
arxiv.org
Neural language models are black-boxes -- both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to...
0
7
0
RT @JohnCLangford: A new opening for multimodal model research: . Please apply if interested.
0
11
0
RT @ShamKakade6: 1/6 Infinite-dim SGD in linear regression is the strawman model for studying scaling laws, critical batch sizes, and LR sc….
0
30
0
RT @owenoertell: Tired of over-optimized generations that stray too far from the base distribution?.We present SLCD: Supervised Learning ba….
0
10
0
RT @nico_espinosa_d: by incorporating self-consistency during offline RL training, we unlock three orthogonal directions of scaling:. 1. ef….
0
16
0