36 citations · 165 across the 31 of their papers we have counts for
34 papers
Exploring the Design Space of Permutation Diffusion LLMs
Zhe Xu, Mingfu Liang, Kavosh Asadi +16
Permutation generation with language models requires both text-conditioned ranking and a global one-to-one assignment between candidates and output positions. We study this problem…
Recursive Self-Improvement via On-Policy Distillation for Reasoning
Shangjian Yin, Zehao Zhao, Kavosh Asadi +7
On-policy distillation (OPD) trains a student model by having it generate trajectories, then matching its next-token predictions with an external teacher's next-token predictions.…
Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou +5
Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot gene…
The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
Zhe Xu, Prachi Agrawal, Kavosh Asadi +17
Large Language Models (LLMs) have emerged as powerful assets for recommender systems. However, deploying them as generative recommenders or zero-shot rankers at web-scale remains b…
GR2 Technical Report
Yufei Li, Zaiwei Zhang, Mingfu Liang +67
Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step dispropo…
Credit Assignment with Resets in Language Model Reasoning
Ankur Samanta, Akshayaa Magesh, Ayush Jain +7
Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…
Displacement-Resistant Extensions of DPO with Nonconvex -Divergences
Idan Pipano, Shoham Sabach, Kavosh Asadi +1
DPO and related algorithms align language models by directly optimizing the RLHF objective: find a policy that maximizes the Bradley-Terry reward while staying close to a reference…
GR2: Generative Reasoning Re-ranker
Mingfu Liang, Yufei Li, Jay Xu +20
Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work h…
Structure Enables Effective Self-Localization of Errors in LLMs
Ankur Samanta, Akshayaa Magesh, Ayush Jain +8
Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward buildin…
Learning to Reason Efficiently with Discounted Reinforcement Learning
Alex Ayoub, Kavosh Asadi, Dale Schuurmans +2
Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to…
InstructVTON: Optimal Auto-Masking and Natural-Language-Guided Interactive Style Control for Inpainting-Based Virtual Try-On
Julien Han, Shuwen Qiu, Qi Li +4
We present InstructVTON, an instruction-following interactive virtual try-on system that allows fine-grained and complex styling control of the resulting generation, guided by natu…
C2-DPO: Constrained Controlled Direct Preference Optimization
Kavosh Asadi, Julien Han, Idan Pipano +5
Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations…
Adjoint sharding for very long context training of state space models
Xingzi Xu, Amir Tavanaei, Kavosh Asadi +1
Despite very fast progress, efficiently training large language models (LLMs) in very long contexts remains challenging. Existing methods fall back to training LLMs with short cont…
Learning the Target Network in Function Space
Kavosh Asadi, Yao Liu, Shoham Sabach +2
We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ens…
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi +4
The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challe…
Resetting the Optimizer in Deep RL: An Empirical Study
Kavosh Asadi, Rasool Fakoor, Shoham Sabach
We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems…
TD Convergence: An Optimization Perspective
Kavosh Asadi, Shoham Sabach, Yao Liu +2
We study the convergence behavior of the celebrated temporal-difference (TD) learning algorithm. By looking at the algorithm through the lens of optimization, we first argue that T…
Characterizing the Action-Generalization Gap in Deep Q-Learning
Zhiyuan Zhou, Cameron Allen, Kavosh Asadi +1
We study the action generalization ability of deep Q-learning in discrete action spaces. Generalization is crucial for efficient reinforcement learning (RL) because it allows agent…
Faster Deep Reinforcement Learning with Slower Online Network
Kavosh Asadi, Rasool Fakoor, Omer Gottesman +3
Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some dela…
Coarse-Grained Smoothness for RL in Metric Spaces
Omer Gottesman, Kavosh Asadi, Cameron Allen +3
Principled decision-making in continuous state--action spaces is impossible without some assumptions. A common approach is to assume Lipschitz continuity of the Q-function. We show…
Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback
Ishaan Shah, David Halpern, Kavosh Asadi +1
Fluid human-agent communication is essential for the future of human-in-the-loop reinforcement learning. An agent must respond appropriately to feedback from its human trainer even…
Continuous Doubly Constrained Batch Reinforcement Learning
Rasool Fakoor, Jonas Mueller, Kavosh Asadi +2
Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive…
Learning State Abstractions for Transfer in Continuous Control
Kavosh Asadi, David Abel, Michael L. Littman
Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple…
Deep Radial-Basis Value Functions for Continuous Control
Kavosh Asadi, Neev Parikh, Ronald E. Parr +2
A core operation in reinforcement learning (RL) is finding an action that is optimal with respect to a learned value function. This operation is often challenging when the learned…