8 papers
Enhancing Adversarial Transferability through Block Stretch and Shrink
Quan Liu, Feng Ye, Chenhao Lu +4
Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs. Existing analyses mainly explain their efficacy from image…
On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning
Siyi Lyu, Quan Liu, Feng Yan
Vision Transformers (ViTs) excel in semantic recognition but exhibit systematic failures in spatial reasoning tasks such as mental rotation. While often attributed to data scale, t…
PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Yaxuan Wang, Quan Liu, Zhenting Wang +4
Large language models (LLMs) underpin applications in code generation, mathematical reasoning, and agent-based workflows. In practice, systems access LLMs via commercial APIs or op…
Spark-Prover-X1: Formal Theorem Proving Through Diverse Data Training
Xinyuan Zhou, Yi Lei, Xiaoyu Zhou +7
Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal langu…
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
Yaxuan Wang, Chris Yuhao Liu, Quan Liu +4
Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning…
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
Zhenting Wang, Qi Chang, Hemani Patel +8
We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter cont…