1 citations · 2 across the 10 of their papers we have counts for
13 papers
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
Ha Minh Hieu, Tongyao Zhu, Do Xuan Long +1
LLM-driven evolutionary search is a promising paradigm for scientific discovery, but existing methods remain costly and slow, often applying expensive reasoning uniformly while und…
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long +12
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesi…
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
Tongyao Zhu, Chao-Ming Huang, Min-Yen Kan
While mixed-language querying is ubiquitous in multilingual communities, the sensitivity of dense retrievers to such queries remains poorly understood. We present a ratio-controlle…
SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
Shiqi Chen, Jingze Gai, Ruochen Zhou +13
Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but…
Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
Shiqi Chen, Tongyao Zhu, Zian Wang +8
Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call exploration collapse: under reinforcement lear…
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
Haonan Wang, Weida Liang, Zihang Fu +8
Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this…
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
Shiqi Chen, Jinghan Zhang, Tongyao Zhu +5
Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these tw…
SkyLadder: Better and Faster Pretraining via Context Window Scheduling
Tongyao Zhu, Qian Liu, Haonan Wang +4
Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences. However, our pilot study reveals that models pretrained with shorte…
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
Shiqi Chen, Tongyao Zhu, Ruochen Zhou +7
Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing "under" or "behind" rel…
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
Longxu Dou, Qian Liu, Fan Zhou +38
Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Haonan Wang, Qian Liu, Chao Du +4
Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de f…
CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
Yixi Ding, Jiaying Wu, Tongyao Zhu +3
To broaden the dissemination of scientific knowledge to diverse audiences, it is desirable for scientific document summarization systems to simultaneously control multiple attribut…
Beyond Memorization: The Challenge of Random Memory Access in Language Models
Tongyao Zhu, Qian Liu, Liang Pang +3
Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge st…