Jian Yang

SemPIC boosts long-context retrieval performance by 13% over traditional KV caching, nearing the efficiency of full recompute without sacrificing model integrity.

AlphaSchema reveals that systematic exploration of trading semantics can significantly enhance alpha mining effectiveness, yielding robust predictive performance across various LLMs.

Achieving a harmonious balance between facial fidelity and overall appearance consistency could redefine personalized image generation.

Leveraging resolution differences can yield significant performance gains in multimodal large language models without the need for external supervision or annotations.

LLMs that can generate HTML are finally useful: HTMLCure's closed-loop repair engine turns superficially correct but broken pages into high-quality training data, rivaling the performance of much larger models.

Relight 3D assets 25x faster with a feed-forward network that distills relightable representations from large reconstruction models, sidestepping expensive per-scene optimization.

Stop LLMs from drifting to English when reasoning in other languages: language-adaptive RL can guide them to stay consistent without sacrificing performance.

By intelligently incorporating LiDAR-derived height information, HiPR overcomes limitations of fixed projection spaces, achieving state-of-the-art camera-LiDAR occupancy prediction with real-time performance.

LLM agents can achieve near-impregnable defense against prompt injection with minimal utility loss by borrowing classic operating system virtualization techniques.

Industrial code generation gets a reasoning boost: InCoder-32B-Thinking leverages error-driven feedback and a code world model to achieve top-tier performance on complex hardware-aware tasks.