From the 1 of 7 linked papers with an AI index.
7 papers
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
Yiming Zeng, Lei Lu, Zexin Li +9
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capacity by storing multiple ful…
MUGEN: A Unified Framework for Efficient Motion Understanding and Generation
Zhankai Ye, Yukai Jin, Bingyang Wei +5
The paper introduces MUGEN, a unified framework that uses a single adaptive-length autoencoder to compress human motion into continuous latent slots, enabling efficient text-to-mot…
SALT: Salience-Aware Lexical Trie for Long-Context Compression
Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury +2
As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-le…
GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
Zhankai Ye, Bofan Li, Yukai Jin +5
Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, exis…
TreeDiff: AST-Guided Code Generation with Diffusion LLMs
Yiming Zeng, Jinghan Cao, Zexin Li +7
Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, cod…
Dynamic Bayesian Optimization Framework for Instruction Tuning in Partial Differential Equation Discovery
Junqi Qu, Yan Zhang, Shangqian Gao +1
Large Language Models (LLMs) show promise for equation discovery, yet their outputs are highly sensitive to prompt phrasing, a phenomenon we term instruction brittleness. Static pr…