12 papers
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
Ke Li, Dong An, Xiaoling Zang +6
Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but tha…
Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration
Lu Yue, Yue Fan, Shiwei Lian +4
Zero-shot Vision-and-Language Navigation (VLN) agents leveraging Large Language Models (LLMs) excel in generalization but suffer from insufficient spatial perception. Focusing on c…
Controlling Thinking Speed in Reasoning Models
Zhengkai Lin, Zhihang Fu, Ze Chen +6
Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at…
GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
Zhanwei Zhang, Kaiyuan Liu, Junjie Liu +5
Local geometry-controllable computer-aided design (CAD) generation aims to modify local parts of CAD models automatically, enhancing design efficiency. It also ensures that the sha…
Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents
Tianmi Ma, Jiawei Du, Wenxin Huang +4
Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks, yet their performance in dynamic, real-world financial environments remains undere…
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
Chenxi Huang, Shaotian Yan, Liang Xie +6
Representation Fine-tuning (ReFT), a recently proposed Parameter-Efficient Fine-Tuning (PEFT) method, has attracted widespread attention for significantly improving parameter effic…