Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Paper • 2607.28611 • Published • 19
Adobe
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Wonder: Video World Model Done Better
taesiri
submitted a
paper to Daily Papers 5 days ago
taesiri
submitted a
paper to Daily Papers 7 days ago
shariqfarooq
submitted a
paper to Daily Papers about 2 months ago
hryou1998
submitted a
paper to Daily Papers about 2 months ago
ShuhongZheng
submitted a
paper to Daily Papers 2 months ago
taesiri
submitted a
paper to Daily Papers 5 months ago
jacklishufan
submitted a
paper to Daily Papers 5 months ago
subhojyoti1990
authored 13
papers 5 months ago
Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
Paper • 2406.05064 • Published
Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization
Paper • 2412.05469 • Published
Optimal Design for Human Preference Elicitation
Paper • 2404.13895 • Published
Partial Policy Gradients for RL in LLMs
Paper • 2603.06138 • Published
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
Paper • 2506.06964 • Published
From Selection to Generation: A Survey of LLM-based Active Learning
Paper • 2502.11767 • Published • 3
A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
Paper • 2507.07202 • Published • 25
A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
Paper • 2505.14106 • Published
MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
Paper • 2510.08783 • Published • 5
Logits are All We Need to Adapt Closed Models
Paper • 2502.06806 • Published
StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
Paper • 2512.01707 • Published • 8
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8
Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
Paper • 2602.13028 • Published