VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding
Paper • 2602.10146 • Published
Huan Li
longaspire
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding authored a paper 2 days ago
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity authored a paper 2 days ago
LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)Organizations
None yet
authored 13
papers 2 days ago
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Paper • 2608.23392 • Published • 28
LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)
Paper • 2606.09004 • Published • 2
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
Paper • 2604.05546 • Published • 1
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
Paper • 2605.11814 • Published • 2
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Paper • 2605.09681 • Published • 10
Token Economics for LLM Agents: A Dual-View Study from Computing and Economics
Paper • 2605.09104 • Published • 6
CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization
Paper • 2510.17847 • Published
AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
Paper • 2511.23475 • Published • 44
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
Paper • 2502.04395 • Published
AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference
Paper • 2504.10326 • Published • 25
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
Paper • 2502.13533 • Published • 13
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
Paper • 2309.08168 • Published
upvoted a paper 2 days ago
upvoted a paper 10 days ago
upvoted a paper 3 months ago
upvoted 3
papers 4 months ago
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
Paper • 2605.11814 • Published • 2
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Paper • 2605.09681 • Published • 10
Token Economics for LLM Agents: A Dual-View Study from Computing and Economics
Paper • 2605.09104 • Published • 6