Awesome post-training

Papers

Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification (2026)
Yuxuan Wan et al.
1.94
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation (2026)
Zihan Su et al.
1.94
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music (2026)
Sreyan Ghosh et al.
1.94
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains (2026)
Haoxiang Jiang et al.
1.94
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better (2026)
Gengluo Li et al.
1.94
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding (2026)
Hayate Iso et al.
1.83
Learning to Detect Language Model Training Data via Active Reconstruction (2026)
Junjie Oscar Yin et al.
1.72
Agentic Reasoning for Large Language Models (2026)
Tianxin Wei et al.
1.67
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning? (2025)
Junhao Cheng et al.
1.28
When Models Reason in Your Language: Controlling Thinking Trace Language Comes at the Cost of Accuracy (2025)
Jirui Qi et al.
1.28
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs (2025)
Yufa Zhou et al.
1.28
Improving large language models with concept-aware fine-tuning (2025)
Michael K. Chen et al.
1.28
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing (2025)
Jeffrey Amico et al.
1.28
Scaling Agents via Continual Pre-training (2025)
Liangcai Su et al.
1.28
Beyond Outliers: A Study of Optimizers Under Quantization (2025)
Georgios Vlassis et al.
1.28
Visual Jigsaw Post-Training Improves MLLMs (2025)
Penghao Wu et al.
1.28
From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images (2025)
Yiming Chen et al.
1.28
Rethinking Chain-of-Thought Reasoning for Videos (2025)
Yiwu Zhong et al.
1.28