activity
20182026
most citedGlobal convergence of neuron birth-death dynamics

15 citations · 22 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

18 papers · 1 filter

cs.LG2026

TailSFT: Filtered Fine-Tuning Improves Post-Training Performance

Sadhika Malladi, Samy Jelassi, Dylan Foster +2

Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tu…

cs.LG2026

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding

Costin-Andrei Oncescu, Depen Morwani, Samy Jelassi +3

Transformers process tokens in parallel but are temporally shallow: at position , each layer attends to key-value pairs computed based on the previous layer, yielding a depth ca…

cs.LG2026

Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models

Samy Jelassi, Mujin Kwun, Rosie Zhao +5

Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level beh…

cs.LG2025

Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs

Rachit Bansal, Aston Zhang, Rishabh Tiwari +8

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can co…

cs.LG2025

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones

Parsa Mirtaheri, Ezra Edelman, Samy Jelassi +2

Inference-time computation has emerged as a promising scaling axis for improving large language model reasoning. However, despite yielding impressive performance, the optimal alloc…

cs.LG2025

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Rosie Zhao, Alexandru Meterez, Sham Kakade +3

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of fr…