Daily Papers of 2025-07-14

1. Test-Time Scaling with Reflective Generative Model 89 upvotes, #1 of 2025-07-14
2. Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning 68 upvotes, #2 of 2025-07-14
3. NeuralOS: Towards Simulating Operating Systems via Neural Generative Models 67 upvotes, #3 of 2025-07-14
4. Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation 58 upvotes, #4 of 2025-07-14
5. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities 53 upvotes, #5 of 2025-07-14
6. CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering 50 upvotes, #6 of 2025-07-14
7. KV Cache Steering for Inducing Reasoning in Small Language Models 38 upvotes, #7 of 2025-07-14
8. One Token to Fool LLM-as-a-Judge 29 upvotes, #8 of 2025-07-14
9. Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective 28 upvotes, #9 of 2025-07-14
10. Neural-Driven Image Editing 25 upvotes, #10 of 2025-07-14
11. From One to More: Contextual Part Latents for 3D Generation 17 upvotes, #11 of 2025-07-14
12. Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models 9 upvotes, #12 of 2025-07-14
13. BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity 8 upvotes, #13 of 2025-07-14
14. What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models 7 upvotes, #14 of 2025-07-14
15. Robust Multimodal Large Language Models Against Modality Conflict 5 upvotes, #15 of 2025-07-14
16. Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection 2 upvotes, #16 of 2025-07-14
17. DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging 1 upvotes, #17 of 2025-07-14

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.