Artificial Intelligence

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning ACL 2026 Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs CVPR 2026 Thinking beyond the anthropomorphic paradigm benefits LLM research ACL 2026 Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models CVPR 2026 Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning AAAI 2026 Thinking in 360deg: Humanoid Visual Search in the Wild CVPR 2026 Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World CVPR 2026 Thinking in Schemas: Robust Syllogistic Reasoning in LLMs ACL 2026 Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding CVPR 2026 Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models EACL 2026 Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding CVPR 2026 Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model CVPR 2026 Thinking with Programming Vision: Towards a Unified View for Thinking with Images CVPR 2026 Thinking with Reasoning Skills: Fewer Tokens, More Accuracy ACL 2026 Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm CVPR 2026 Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation ACL 2026 Think in Sentences: Explicit Sentence Boundaries Enhance Language Model’s Capabilities ACL 2026 Think-J: Learning to Think for Generative LLM-as-a-Judge AAAI 2026 Think Just Enough: Leveraging Self-Assessed Confidence for Adaptive Reasoning in Language Models EACL 2026 Think Less, Code Better: Probing When Chain-of-Thought Hurts and How to Route Around It ACL 2026 Think Like You Execute: Verifiable Chain of Thought from Program Traces ACL 2026 Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning ACL 2026 ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling EACL 2026 Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation ACL 2026 ThinkPersona: Thinking with Persona Graphs for Faithful Individualized Role-Playing ACL 2026