collaborators

9 papers

cs.CL2026

Position: It's Time to Optimize LLMs for Self-Consistency

Itamar Pres, Belinda Z. Li, Laura Ruis +6

Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy")…

cs.LG2026

Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations

Mehul Damani, Isha Puri, Idan Shenfeld +1

RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning…

cs.LG2026

Vector Policy Optimization: Training for Diversity Improves Test-Time Search

Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld +6

Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a varie…

cs.LG2026

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

Mehul Damani, Isha Puri, Stewart Slocum +4

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult questio…

cs.LG2026

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

Isha Puri, Mehul Damani, Idan Shenfeld +3

Given a question, a language model (LM) implicitly encodes a distribution over possible answers. In practice, post-training procedures for LMs often collapse this distribution onto…

cs.LG2026

CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control

Yifeng Zhang, Harsh Goel, Peizhuo Li +3

Adaptive traffic signal control (ATSC) is crucial in alleviating congestion, maximizing throughput and promoting sustainable mobility in ever-expanding cities. Multi-Agent Reinforc…