11 papers
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
Gagan Mundada, Zihan Huang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled tra…
ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
Xin Xu, Tong Yu, Xiang Chen +3
Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effect…
Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
Xiangchi Yuan, Xiang Chen, Tong Yu +4
Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substa…
Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Rongzhi Zhang, Liqin Ye, Yuzhao Heng +5
Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse…
Towards Improving Long-Tail Entity Predictions in Temporal Knowledge Graphs through Global Similarity and Weighted Sampling
Mehrnoosh Mirtaheri, Ryan A. Rossi, Sungchul Kim +4
Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training. This overlooks challenges stemming from the evolving nature of TKG…
Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
Paiheng Xu, Gang Wu, Xiang Chen +6
Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specifi…
WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion
Vinay Shukla, Prachee Sharma, Ryan Rossi +3
The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Curre…
Benchmarking Reasoning Robustness in Large Language Models
Tong Yu, Yongcheng Jing, Xikun Zhang +6
Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: s…
Exploring Rewriting Approaches for Different Conversational Tasks
Md Mehrab Tanjim, Ryan A. Rossi, Mike Rimer +9
Conversational assistants often require a question rewriting algorithm that leverages a subset of past interactions to provide a more meaningful (accurate) answer to the user's que…
From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
Manisha Mukherjee, Sungchul Kim, Xiang Chen +3
The Adobe Experience Platform AI Assistant is a conversational tool that enables organizations to interact seamlessly with proprietary enterprise data through a chatbot. However, d…
Pandora with Inaccurate Priors
Kiarash Banihashem, Xiang Chen, MohammadTaghi Hajiaghayi +4
We investigate the role of inaccurate priors for the classical Pandora's box problem. In the classical Pandora's box problem we are given a set of boxes each with a known cost and…