25 papers
Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers
Xin Gao, Xingming Xu
Transformer architectures form the foundation of modern natural language processing, yet the Key-Value (KV) cache introduces substantial memory and bandwidth overhead during long-c…
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Jiaoyang Ruan, Xin Gao, Yinda Chen +5
While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces…
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
Zheng Liu, Honglin Lin, Chonghan Qin +13
Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training…
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
Donghao Zhou, Guisheng Liu, Hao Yang +9
In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on text, reference image…
Camyla: Scaling Autonomous Research in Medical Image Segmentation
Yifan Gao, Haoyue Li, Feng Yuan +3
We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded resear…
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
Yu Li, Xiaoran Shang, Qizhi Pei +11
Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic…