179 citations · 285 across the 15 of their papers we have counts for
15 papers
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")…
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…
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…
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…
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…
Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter +1
Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-pol…
Latency and Token-Aware Test-Time Compute
Jenny Y. Huang, Mehul Damani, Yousef El-Kurdi +2
Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However,…
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…
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
Ekin Akyürek, Mehul Damani, Adam Zweiger +5
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number…
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Mehul Damani, Idan Shenfeld, Andi Peng +2
Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code gene…
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Stephen Casper, Xander Davies, Claudia Shi +29
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of…
SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control
Harsh Goel, Yifeng Zhang, Mehul Damani +1
Many recent works have turned to multi-agent reinforcement learning (MARL) for adaptive traffic signal control to optimize the travel time of vehicles over large urban networks. Ho…
Distributed Reinforcement Learning for Robot Teams: A Review
Yutong Wang, Mehul Damani, Pamela Wang +2
Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising app…
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
Florian Laurent, Manuel Schneider, Christian Scheller +24
The Flatland competition aimed at finding novel approaches to solve the vehicle re-scheduling problem (VRSP). The VRSP is concerned with scheduling trips in traffic networks and th…
PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong
Mehul Damani, Zhiyao Luo, Emerson Wenzel +1
Multi-agent path finding (MAPF) is an indispensable component of large-scale robot deployments in numerous domains ranging from airport management to warehouse automation. In parti…