From the 1 of 14 linked papers with an AI index.
14 papers
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Shaoxiong Zhan, Shi Hu, Boyu Feng +7
The paper introduces MM-IssueLoc, a benchmark for evaluating how visual evidence like screenshots can aid repository-level issue localization, providing controlled text-only and mu…
Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
Hai Lin, Hoilam Pao, Shaoxiong Zhan +1
Large language models are undergoing a transition from model technology to system technology. Engineering challenges like cache reuse, context capacity, agent scheduling, and permi…
RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
Wen Huang, Jiarui Yang, Tao Dai +4
Visual manipulation localization (VML) aims to identify tampered regions in images and videos, a task that has become increasingly challenging with the rise of advanced editing too…
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
Zheng Liu, Longxiang Zhang, Xintong Wang +8
LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups wh…
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Yanyu Zhu, Hoilam Pao, Niu Hu +6
Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by static configurations like…
3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
Shaoxiong Zhan, Yanlin Lai, Zheng Liu +6
Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability m…