128 results on '"Gao Huang"'
Search Results
2. Efficient Diffusion Transformer with Step-Wise Dynamic Attention Mediators.
3. GRA: Detecting Oriented Objects Through Group-Wise Rotating and Attention.
4. Rethinking the Architecture Design for Efficient Generic Event Boundary Detection.
5. Agent Attention: On the Integration of Softmax and Linear Attention.
6. AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation.
7. Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering.
8. Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation Without Manual Labels.
9. LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images.
10. Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis.
11. Mask Grounding for Referring Image Segmentation.
12. Exploring Text-to-Motion Generation with Human Preference.
13. Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models.
14. GSVA: Generalized Segmentation via Multimodal Large Language Models.
15. Prompt-Free Diffusion: Taking 'Text' Out of Text-to-Image Diffusion Models.
16. DyFADet: Dynamic Feature Aggregation for Temporal Action Detection.
17. Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model.
18. Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train.
19. PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents.
20. Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling.
21. ExpeL: LLM Agents Are Experiential Learners.
22. Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation.
23. SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning.
24. ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process.
25. Dynamic Perceiver for Efficient Visual Recognition.
26. Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm.
27. Deep Incubation: Training Large Models by Divide-and-Conquering.
28. Adaptive Rotated Convolution for Rotated Object Detection.
29. EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones.
30. FLatten Transformer: Vision Transformer using Focused Linear Attention.
31. Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information.
32. BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision.
33. Siamese Image Modeling for Self-Supervised Vision Representation Learning.
34. Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning.
35. Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention.
36. A graph reasoning method for multi-object unordered stacking scenarios.
37. Human-Riding Inspired Acceleration Control of a Wheel-Legged Humanoid Robot.
38. Boosting Offline Reinforcement Learning with Action Preference Query.
39. Learning to Estimate 3-D States of Deformable Linear Objects from Single-Frame Occluded Point Clouds.
40. Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism.
41. Boosted Dynamic Neural Networks.
42. Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning.
43. Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy.
44. AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition.
45. AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks.
46. DiSparse: Disentangled Sparsification for Multitask Model Compression.
47. Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding.
48. Vision Transformer with Deformable Attention.
49. Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework.
50. On the Integration of Self-Attention and Convolution.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.