3 papers
cs.LG2026
RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents
Sayak Chakrabarti, Sathish Reddy Indurthi
Group Relative Policy Optimization (GRPO) avoids a separate critic by estimating advantages from rollout groups. For multi-turn agents, however, trajectory-level supervision provid…
cs.LG2026
Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers
Sayak Chakrabarti, Toniann Pitassi, Josh Alman
Quantization reduces the numerical precision of Transformer computations and is widely used to accelerate inference, yet its effect on expressivity remains poorly characterized. We…
cs.LG2026
Poly-attention: a general scheme for higher-order self-attention
Sayak Chakrabarti, Toniann Pitassi, Josh Alman
The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown th…