Text-Centric Post-Training for Omni-Modal Reasoning
cs.CL
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/huggingface/open-r1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers
- OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
- Adaptive Backtracking Line Search
- Efficient Lifelong Learning with A-GEM
- OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
- OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
- Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
- OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
- Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
- ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
- OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
- OmniGAIA: Towards Native Omni-Modal AI Agents
- Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
- Instella: Fully Open Language Models with Stellar Performance
- X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
- ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
- AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
- C$^3$PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering