token budget

A More Word-like Image Tokenization for MLLMs CVPR 2026 Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement AAAI 2026 Promoting Efficient Reasoning with Verifiable Stepwise Reward AAAI 2026 SABER: Switchable and Balanced Training for Efficient LLM Reasoning AAAI 2026 Scaling Data-Constrained Language Models with Synthetic Data EACL 2026 State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models AAAI 2026 An Architecture Search Framework for Inference-Time Techniques ICML 2025 DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models EMNLP 2025 DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding CVPR 2025 Overtrained Language Models Are Harder to Fine-Tune ICML 2025 Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models EMNLP 2025 𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation ACL 2025