activity
20242026
collaborators

9 papers

cs.CV2026

Tuning-free Visual Effect Transfer across Videos

Maxwell Jones, Rameen Abdal, Or Patashnik +4

We present RefVFX, a new framework that transfers complex temporal effects from a reference video onto a target video or image in a feed-forward manner. While existing methods exce…

cs.LG2026

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration

Yuxiao Qu, Amrith Setlur, Virginia Smith +2

Reinforcement learning (RL) has improved the reasoning abilities of large language models (LLMs), yet state-of-the-art methods still fail to learn on many training problems. On har…

cs.AI2025

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Yuxiao Qu, Anikait Singh, Yoonho Lee +4

Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems…

cs.LG2025

Rethinking Thinking Tokens: LLMs as Improvement Operators

Lovish Madaan, Aniket Didolkar, Suchin Gururangan +6

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This res…

cs.LG2025

InSTA: Towards Internet-Scale Training For Agents

Brandon Trabucco, Gunnar Sigurdsson, Robinson Piramuthu +1

The predominant approach for training web navigation agents is to gather human demonstrations for a set of popular websites and hand-written tasks, but it is becoming clear that hu…

cs.LG2025

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur +4

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or ru…