AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
Paper • 2609.08572 • Published • 100
Yunyang Xiong
yunyangx
AI & ML interests
Foundation model optimization; Multi-modal LLM
Recent Activity
authored a paper 10 days ago
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems authored a paper 10 days ago
Exploring Audio Hallucination in Egocentric Video Understanding authored a paper 10 days ago
VLM3: Vision Language Models Are Native 3D LearnersOrganizations
authored 19
papers 10 days ago
Exploring Audio Hallucination in Egocentric Video Understanding
Paper • 2604.23860 • Published
VLM3: Vision Language Models Are Native 3D Learners
Paper • 2605.30561 • Published • 25
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Paper • 2604.08120 • Published • 20
Neural Computers
Paper • 2604.06425 • Published • 30
Efficient Universal Perception Encoder
Paper • 2603.22387 • Published • 11
EgoAVU: Egocentric Audio-Visual Understanding
Paper • 2602.06139 • Published • 12
EdgeTAM: On-Device Track Anything Model
Paper • 2501.07256 • Published • 3
ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization
Paper • 2502.02631 • Published • 5
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
Paper • 2412.14164 • Published • 4
Agent-as-a-Judge: Evaluate Agents with Agents
Paper • 2410.10934 • Published • 23
Fast Point Cloud Generation with Straight Flows
Paper • 2212.01747 • Published
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Paper • 2111.09714 • Published
SqueezeSAM: User friendly mobile interactive segmentation
Paper • 2312.06736 • Published
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Paper • 2306.04845 • Published • 4
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
Paper • 2102.03902 • Published
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Paper • 2312.00863 • Published • 4
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
Paper • 2004.14525 • Published
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Paper • 2310.09478 • Published • 22
upvoted a paper 10 days ago