Yujun Cai

DICE transforms long-document retrieval by effectively preserving critical information from chunks, achieving up to a 60% increase in retrieval accuracy for documents over 4,000 tokens.

SelectStream reveals that selective memory allocation can dramatically enhance streaming video understanding, outperforming traditional methods by preserving scene perception without sacrificing performance.

LLMs can now reliably generate complex, editable SVG diagrams by explicitly optimizing for geometric constraints via reinforcement learning, opening the door to automated technical illustration.

Forget flattening: VideoStir's spatio-temporal graph retrieval and intent-aware scoring unlocks more effective reasoning over long videos.

FactGuard's agentic framework substantially boosts video misinformation detection by strategically using external tools and reinforcement learning to overcome the inherent limitations of relying solely on internal MLLM reasoning.

Forget expensive retraining: PromptCD unlocks significant improvements in LLM alignment and VLM visual grounding simply by contrasting model responses to cleverly designed prompts at test time.

Time series generation can be dramatically improved by explicitly conditioning on semantic understanding, as demonstrated by a novel vision-centric framework.