| MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization | Jul 14, 2025 | 2kImage Generation | CodeCode Available | 2 |
| MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization | Jul 10, 2025 | 2kQuantization | CodeCode Available | 2 |
| Understanding and Improving Length Generalization in Recurrent Models | Jul 3, 2025 | 2kState Space Models | —Unverified | 0 |
| A strengthened bound on the number of states required to characterize maximum parsimony distance | Jun 11, 2025 | 2k | —Unverified | 0 |
| Structured Variational D-Decomposition for Accurate and Stable Low-Rank Approximation | Jun 10, 2025 | 2k | —Unverified | 0 |
| Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free | May 31, 2025 | 2k4k | —Unverified | 0 |
| Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning | May 30, 2025 | 2k | —Unverified | 0 |
| Test-Time Training Done Right | May 29, 2025 | 2kNovel View Synthesis | —Unverified | 0 |
| Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models | May 29, 2025 | 2k4k | CodeCode Available | 1 |
| MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database | May 25, 2025 | 2kDiversity | CodeCode Available | 1 |
| Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions | May 23, 2025 | 2kBenchmarking | CodeCode Available | 1 |
| PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues | May 22, 2025 | 2k | —Unverified | 0 |
| Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning | May 19, 2025 | 2kMathematical Reasoning | —Unverified | 0 |
| UIShift: Enhancing VLM-based GUI Agents through Self-supervised Reinforcement Learning | May 18, 2025 | 2kReinforcement Learning (RL) | —Unverified | 0 |
| ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation | May 12, 2025 | 2kRecommendation Systems | CodeCode Available | 0 |
| Calibrating Translation Decoding with Quality Estimation on LLMs | Apr 26, 2025 | 2kMachine Translation | CodeCode Available | 0 |
| aiXamine: Simplified LLM Safety and Security | Apr 21, 2025 | 2kAdversarial Robustness | —Unverified | 0 |
| Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis | Apr 20, 2025 | 2kKnowledge Distillation | —Unverified | 0 |
| Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading | Apr 16, 2025 | 2kCode Generation | —Unverified | 0 |
| On Linear Representations and Pretraining Data Frequency in Language Models | Apr 16, 2025 | 2kIn-Context Learning | —Unverified | 0 |
| Seedream 3.0 Technical Report | Apr 15, 2025 | 2kImage Generation | —Unverified | 0 |
| ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration | Apr 11, 2025 | 2kImage Restoration | —Unverified | 0 |
| FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution | Apr 9, 2025 | 2kDecision Making | CodeCode Available | 3 |
| FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning | Mar 30, 2025 | 2kGPU | CodeCode Available | 2 |
| TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes | Mar 30, 2025 | 2kImage Generation | CodeCode Available | 2 |
