OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
Paper • 2510.06751 • Published • 22
AI & ML interests
None defined yet.
Papers
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
Huan-WhoRegisteredMyName
authored 2
papers 11 months ago
Huan-WhoRegisteredMyName
authored 4
papers about 1 year ago
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios
Paper • 2507.20198 • Published • 28
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
Paper • 2503.16257 • Published • 28
Is Oracle Pruning the True Oracle?
Paper • 2412.00143 • Published • 3
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Paper • 2505.21334 • Published • 21
Huan-WhoRegisteredMyName
authored 10
papers over 1 year ago
Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps
Paper • 2505.18675 • Published • 29
Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View
Paper • 2503.12553 • Published • 8
Image as Set of Points
Paper • 2303.01494 • Published
Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution
Paper • 2303.09650 • Published
Frame Flexible Network
Paper • 2303.14817 • Published
What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective
Paper • 2012.02909 • Published • 2
R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
Paper • 2203.17261 • Published • 1
Real-Time Neural Light Field on Mobile Devices
Paper • 2212.08057 • Published
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Paper • 2411.15024 • Published • 2
Autoregressive Image Generation with Randomized Parallel Decoding
Paper • 2503.10568 • Published • 9
Huan-WhoRegisteredMyName
authored a
paper about 3 years ago