collaborators

11 papers

cs.AI2026

Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this gap by rescoring a model's ow…

cs.DC2026

Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…

cs.LG2026

Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts

Xuan-Phi Nguyen, Shrey Pandit, Austin Xu +2

Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that ev…

cs.CL2025

Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms

Shrey Pandit, Xuan-Phi Nguyen, Yifei Ming +4

Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underly…

cs.AI2025

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

Shrey Pandit, Austin Xu, Xuan-Phi Nguyen +3

Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive fu…

cs.AI2025

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy +4

Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances…