10 citations · 37 across the 22 of their papers we have counts for
22 papers
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
Han Zhou, Adam X. Yang, Laurence Aitchison +2
Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models through outcome-based supervision.…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
Voxtral Realtime
Mistral-AI, :, Alexander H. Liu +166
We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…
Agentic Policy Optimization via Instruction-Policy Co-Evolution
Han Zhou, Xingchen Wan, Ivan Vulić +1
Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective m…
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Chengzu Li, Zanyi Wang, Jiaang Li +9
Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the d…
Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
Xingchen Wan, Han Zhou, Ruoxi Sun +4
Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manu…
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Jinyuan Fang, Yanwen Peng, Xi Zhang +12
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manua…
SEW: Self-Evolving Agentic Workflows for Automated Code Generation
Siwei Liu, Jinyuan Fang, Han Zhou +2
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on cr…
Visual Planning: Let's Think Only with Images
Yi Xu, Chengzu Li, Han Zhou +4
Recent advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have substantially enhanced machine reasoning across diverse tasks. However, these model…
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Han Zhou, Xingchen Wan, Ruoxi Sun +5
Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts tha…
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
Xingchen Wan, Han Zhou, Ruoxi Sun +3
Recent advances in long-context large language models (LLMs) have led to the emerging paradigm of many-shot in-context learning (ICL), where it is observed that scaling many more d…
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
Chengzu Li, Caiqi Zhang, Han Zhou +3
Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `no…
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
Han Zhou, Xingchen Wan, Yinhong Liu +3
Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM e…
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
Yinhong Liu, Han Zhou, Zhijiang Guo +4
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit bi…
Large Language Models are Miscalibrated In-Context Learners
Chengzu Li, Han Zhou, Goran Glavaš +2
When adapting ICL with or without fine-tuning, we are curious about whether the instruction-tuned language model is able to achieve well-calibrated results without suffering from t…
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Songbo Hu, Han Zhou, Moy Yuan +5
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically…
Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning
Han Zhou, Xingchen Wan, Ivan Vulić +1
Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning. Black-box prompt search has received…
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Han Zhou, Xingchen Wan, Lev Proleev +4
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias fac…
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Songbo Hu, Han Zhou, Mete Hergul +5
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, cul…
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
Han Zhou, Xingchen Wan, Ivan Vulić +1
Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning…
GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost
Qingcheng Zeng, Lucas Garay, Peilin Zhou +7
Large pre-trained models have revolutionized natural language processing (NLP) research and applications, but high training costs and limited data resources have prevented their be…
XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
Han Zhou, Ignacio Iacobacci, Pasquale Minervini
Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD) systems, keeps track of all important information pertaining to dialogue history: filling slots w…