π“Ÿ host1.bitchan.one

𓀐 @6~+?tyNV

⏱ 2d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

>mfw Research news 06/11/2025 >SeedEdit 3.0: Fast and High-Quality Generative Image Editing https://seed.bytedance.com/tech/seededit >CIVET: Systematic Evaluation of Understanding in VLMs https://arxiv.org/abs/2506.05146 >Refer to Anything with Vision-Language Prompts https://Ref2Any.github.io >HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation https://research.nvidia.com/labs/dir/hmar >Multi-scale Image Super Resolution with a Single Auto-Regressive Model https://arxiv.org/abs/2506.04990 >APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval https://arxiv.org/abs/2506.04953 >Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations https://arxiv.org/abs/2506.04951 >DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation https://arxiv.org/abs/2506.04830 >Robust Few-Shot Vision-Language Model Adaptation https://hannawang09.github.io/projects/srapf >HoliSafe: Holistic Safety Benchmarking and Modeling with Safety Meta Token for Vision-Language Model https://youngwanlee.github.io/holisafe >Gen-n-Val: Agentic Image Data Generation and Validation https://arxiv.org/abs/2506.04676 >Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts https://arxiv.org/abs/2506.04673 >FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion https://fps.ziplab.co >Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders https://arxiv.org/abs/2506.04641 >Video World Models with Long-term Spatial Memory https://spmem.github.io >Contrastive Flow Matching https://arxiv.org/abs/2506.05350 >Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos https://Perceive-Anything.github.io⏱ 2d↩ 1
year old news >mfw Research news 11/05/2026 >DualCast: Dual-Image Conditioned Diffusion Transformers for Digital Human E-Commerce Video Generation https://arxiv.org/abs/2611.05825 >DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion https://arxiv.org/abs/2611.05917 >Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation https://arxiv.org/abs/2611.05578 >Chronos: Sequential Identity-Preserving Video Generation by Temporal Anchoring https://arxiv.org/abs/2611.05893 >PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMs https://arxiv.org/abs/2611.04948 >NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation https://arxiv.org/abs/2611.06270 >Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models https://arxiv.org/abs/2611.05755 >Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline https://arxiv.org/abs/2611.06000 >Clips2Story: Training-Free Video Storyboarding and Editing Using Multimodal Retrieval-Embedded Generation https://arxiv.org/abs/2611.05992 >Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling https://arxiv.org/abs/2611.04916 >Wonder 4: A Mixture-of-Experts Recipe for Image Quality Enhancement https://arxiv.org/abs/2611.05294 >SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation https://arxiv.org/abs/2611.06048 >The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models https://arxiv.org/abs/2611.04817 >ScoreDial: Precise Control of Visual Attributes in Image Generation via Regressor Guidance from Limited Human Ratings https://arxiv.org/abs/2611.05004 >CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models https://arxiv.org/abs/2609.20267⏱ 2d↩