collaborators

6 papers

cs.LG2026

Reinforcement Learning from Rich Feedback with Distributional DAgger

Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad

Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward…

cs.LG2026

Solve the Loop: Attractor Models for Language and Reasoning

Jacob Fein-Ashley, Paria Rashidinejad

Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving language modeling and reasoning. Yet…

cs.LG2026

CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing

Zarif Ikram, Arad Firouzkouhi, Stephen Tu +2

A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly game the editing proxy and corr…

cs.CL2026

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Chenyu Wang, Paria Rashidinejad, DiJia Su +9

Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, align…

cs.LG2026

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

Amrith Setlur, Zijian Wang, Andrew Cohen +2

Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls.…

cs.LG2024

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking

Paria Rashidinejad, Yuandong Tian

Aligning AI systems with human preferences typically suffers from the infamous reward hacking problem, where optimization of an imperfect reward model leads to undesired behaviors.…