Tokenization


SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs

Add code
Feb 05, 2026
Viaarxiv icon

Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences

Add code
Feb 05, 2026
Viaarxiv icon

Towards Green AI: Decoding the Energy of LLM Inference in Software Development

Add code
Feb 05, 2026
Viaarxiv icon

CAViT -- Channel-Aware Vision Transformer for Dynamic Feature Fusion

Add code
Feb 05, 2026
Viaarxiv icon

SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation

Add code
Feb 05, 2026
Viaarxiv icon

BLITZRANK: Principled Zero-shot Ranking Agents with Tournament Graphs

Add code
Feb 05, 2026
Viaarxiv icon

Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale

Add code
Feb 05, 2026
Viaarxiv icon

MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors

Add code
Feb 05, 2026
Viaarxiv icon

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

Add code
Feb 05, 2026
Viaarxiv icon

E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching

Add code
Feb 05, 2026
Viaarxiv icon