Guohao Dai
17 papers · 2023–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Conference Polyglot (7) π§ Keyword Pioneer π Renaissance Researcher (5) π Interdisciplinary Bridge π Cross-Pollinator (11)
π§
Keyword Pioneer
π
Grand Slam
π€
Dynamic Duo
(14)
ποΈ
Keyword Collector
(65)
β
The Questioner
β‘
Prolific Year
(5)
π
Century Club
(15)
Conferences
ICCV (4)
ICLR (4)
AAAI (2)
CVPR (2)
NIPS (2)
ECCV (1)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
model compression
(3)
efficient computing
(3)
diffusion transformer
(3)
diffusion model
(3)
image generation
(2)
text-to-image generation
(2)
vision-language model
(2)
large language model
(2)
computational efficiency
(2)
video generation
(2)
in-context learning
(1)
video understanding
(1)
efficient inference
(1)
knowledge distillation
(1)
image synthesis
(1)
power consumption
(1)
generative evaluation
(1)
adaptive inference
(1)
feature similarity
(1)
model evaluation
(1)
Papers
MoSs: Mixture of Scales for Efficient High-Resolution Autoregressive Image Generation
AAAI 2026
SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
AAAI 2026
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
ICCV 2025
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
CVPR 2025
DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate
ICCV 2025
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models
ICCV 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
ICLR 2025
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
ICLR 2025
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
ICLR 2025
DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
ICLR 2025
Efficient Inference for Large Language Models βAlgorithm, Model, and System
EMNLP 2025
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
ECCV 2024
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
NIPS 2024
Evaluating Quantized Large Language Models
ICML 2024
DiTFastAttn: Attention Compression for Diffusion Transformer Models
NIPS 2024
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
CVPR 2024
Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection
ICCV 2023