Daily Papers of 2026-03-03
- OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens 137 upvotes, #1 of 2026-03-03
- From Scale to Speed: Adaptive Test-Time Scaling for Image Editing 134 upvotes, #2 of 2026-03-03
- SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale 80 upvotes, #3 of 2026-03-03
- RubricBench: Aligning Model-Generated Rubrics with Human Standards 55 upvotes, #4 of 2026-03-03
- CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning 48 upvotes, #5 of 2026-03-03
- OpenAutoNLU: Open Source AutoML Library for NLU 46 upvotes, #6 of 2026-03-03
- MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning 42 upvotes, #7 of 2026-03-03
- VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection 35 upvotes, #8 of 2026-03-03
- CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction 32 upvotes, #9 of 2026-03-03
- CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification 23 upvotes, #10 of 2026-03-03
- PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval 20 upvotes, #11 of 2026-03-03
- LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model 19 upvotes, #12 of 2026-03-03
- WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories 17 upvotes, #13 of 2026-03-03
- Spectral Condition for μP under Width-Depth Scaling 15 upvotes, #14 of 2026-03-03
- Efficient RLVR Training via Weighted Mutual Information Data Selection 14 upvotes, #15 of 2026-03-03
- Learn Hard Problems During RL with Reference Guided Fine-tuning 12 upvotes, #16 of 2026-03-03
- Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data 10 upvotes, #17 of 2026-03-03
- Agentic Code Reasoning 9 upvotes, #18 of 2026-03-03
- When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains 8 upvotes, #19 of 2026-03-03
- Legal RAG Bench: an end-to-end benchmark for legal RAG 7 upvotes, #20 of 2026-03-03
- Half-Truths Break Similarity-Based Retrieval 6 upvotes, #21 of 2026-03-03
- Unified Vision-Language Modeling via Concept Space Alignment 6 upvotes, #21 of 2026-03-03
- Spectral Attention Steering for Prompt Highlighting 6 upvotes, #21 of 2026-03-03
- FireRed-OCR Technical Report 6 upvotes, #21 of 2026-03-03
- CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production 6 upvotes, #21 of 2026-03-03
- Tool Verification for Test-Time Reinforcement Learning 6 upvotes, #21 of 2026-03-03
- LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval 5 upvotes, #27 of 2026-03-03
- Recursive Think-Answer Process for LLMs and VLMs 5 upvotes, #27 of 2026-03-03
- Classroom Final Exam: An Instructor-Tested Reasoning Benchmark 4 upvotes, #29 of 2026-03-03
- Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos 4 upvotes, #29 of 2026-03-03
- Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training 4 upvotes, #29 of 2026-03-03
- SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation 3 upvotes, #32 of 2026-03-03
- RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment 3 upvotes, #32 of 2026-03-03
- ArtLLM: Generating Articulated Assets via 3D LLM 3 upvotes, #32 of 2026-03-03
- CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering 2 upvotes, #35 of 2026-03-03
- ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data 1 upvotes, #36 of 2026-03-03
- MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation 1 upvotes, #36 of 2026-03-03
- Using Songs to Improve Kazakh Automatic Speech Recognition 1 upvotes, #36 of 2026-03-03
- Cryo-Bench: Benchmarking Foundation Models for Cryosphere Applications 1 upvotes, #36 of 2026-03-03
- Monocular Mesh Recovery and Body Measurement of Female Saanen Goats 0 upvotes, #40 of 2026-03-03
- Planning from Observation and Interaction 0 upvotes, #40 of 2026-03-03
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.