25 citations · 56 across the 25 of their papers we have counts for
9 papers · 1 filter
Staircase Streaming for Low-Latency Multi-Agent Inference
Junlin Wang, Jue Wang, Zhen +5
Recent advances in large language models (LLMs) opened up new directions for leveraging the collective expertise of multiple LLMs. These methods, such as Mixture-of-Agents, typical…
SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
Junlin Wang, Zehao Wu, Shaowei Lu +2
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the…
When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
Zhen Xu, Shang Zhu, Jue Wang +5
We investigate the challenge of applying Large Language Models (LLMs) to long texts. We propose a theoretical framework that distinguishes the failure modes of long context tasks i…
Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation
Zonghan Wu, Congyuan Zou, Junlin Wang +3
Generative AI, particularly large language models (LLMs), is beginning to transform the financial industry by automating tasks and helping to make sense of complex financial inform…
Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
Junlin Wang, Roy Xie, Shang Zhu +6
Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality hum…
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
Hongyi James Cai, Junlin Wang, Xiaoyin Chen +1
Recent advancements in large language models (LLMs) suggest that reinforcement learning (RL) effectively internalizes search strategies, yielding significant improvements on challe…
Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning
Junlin Wang, Zhiyun Lin
Learning effective visual representations for robotic manipulation remains a fundamental challenge due to the complex body dynamics involved in action execution. In this paper, we…
Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals
Junlin Wang, Shang Zhu, Jon Saad-Falcon +7
There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. While br…
Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
Roy Xie, Junlin Wang, Paul Rosu +4
Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. W…