Kun Li

The paper demonstrates that security patch detection models trained solely on publicly reported vulnerabilities (NVD) perform poorly when tested on real-world, unreported 'in-the-wild' patches, suggesting the need for diverse training data.

TitanCA presents a novel, multi-agent LLM orchestration framework that significantly improves vulnerability discovery by reducing false positives and identifying numerous zero-day vulnerabilities.

ADWIN introduces an adaptive window framework for on-policy distillation (OPD) that efficiently manages the supervision horizon by training on short, teacher-anchored prefixes while using delayed full-rollout probes to maintain alignment, significantly reducing training cost while preserving accuracy.

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improvements for agent behaviors and coordination.

Introduce Parallel-Synthesis, a framework enabling a synthesizer to directly consume parallel agent branches' KV caches, improving efficiency and performance.

The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-art preference accuracy and noise-robustness.

This paper introduces CineCap, a framework for cinematographic captioning using structured reasoning, spatio-temporal anchors, and reinforcement learning.

This paper presents a comprehensive measurement study on the performance and energy consumption of large language models on mobile devices, using five frameworks and three hardware backends, and introduces PowerBench, a tool for fine-grained profiling.

This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.