Chen Yang

The paper proposes VDSB-GWSyn, a Diffusion Schrödinger Bridge framework, to synthesize controllable and anatomically feasible guidewire images on coronary angiography (CAG) scans, significantly improving the performance of guidewire endpoint localization for robot-assisted PCI.

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes and distilling reusable workflow skills.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The paper introduces PlanRAG, a framework for Retrieval-Augmented Generation (RAG) that models exploratory reasoning problems as logical query trees, addressing representation and optimization gaps between structured SQL and unstructured natural language.

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model selection and verification under serving-time conditions.

The paper proposes PagedWeight, a method for managing Mixture-of-Experts (MoE) language model serving in KV-cache-intensive scenarios, achieving FP16-equivalent accuracy with up to 72.0% GPU memory savings and 1.94$ imes$ throughput improvement.

This paper introduces HIJACKKV, the first attack framework to exploit the new threat of KV Cache Hijacking in large language models, achieving an average success rate of 94%.

The paper provides a negative answer to Carlson's question about whether the depth of a finite-group cohomology ring is always realized by the dimension of one of its associated primes.