3D Aware Region Prompted Vision Language Model
Paper • 2509.13317 • Published • 14
AI & ML interests
Inference, reimagined for the agentic era
Team members 3 private
zhijianliu
authored 6
papers 5 months ago
ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
Paper • 2509.04439 • Published • 1
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
Paper • 2510.12872 • Published • 4
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
Paper • 2510.15870 • Published • 93
Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
Paper • 2511.00088 • Published • 4
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
Paper • 2510.17777 • Published • 1
zhijianliu
authored a
paper 6 months ago
zhijianliu
authored 2
papers 8 months ago
zhijianliu
authored a
paper 10 months ago
zhijianliu
authored 10
papers about 1 year ago
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 161
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
Paper • 2506.16500 • Published • 17
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
Paper • 2303.17605 • Published
Deep Leakage from Gradients
Paper • 1906.08935 • Published
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
Paper • 2005.14187 • Published • 2
MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models
Paper • 2308.12963 • Published
TorchSparse: Efficient Point Cloud Inference Engine
Paper • 2204.10319 • Published
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Paper • 2301.08739 • Published
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Paper • 2408.10188 • Published • 52
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Paper • 1802.03494 • Published