Daily Papers of 2025-06-20

1. Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective 42 upvotes, #1 of 2025-06-20
2. Show-o2: Improved Native Unified Multimodal Models 27 upvotes, #2 of 2025-06-20
3. EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection 17 upvotes, #3 of 2025-06-20
4. Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction 10 upvotes, #4 of 2025-06-20
5. SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning 7 upvotes, #5 of 2025-06-20
6. RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation 4 upvotes, #6 of 2025-06-20

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.