More Than Words: Compositional Tokenization for Efficient Language Models
Research
Research News
New papers, breakthroughs and academic AI research
Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection
Research
Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions
Research
RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents
Research
Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning
Research
One Tile, Multiple Instances: Rethinking MIL for Sparse Diagnostic Evidence
Research
MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks
Research
Reflection-Robust 6DoF Object Tracking with Light Fields
Research
TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer
Research
TMAML: Temporal Model-Agnostic Meta-Learning for Cold-Start Time Series Forecasting
Research
Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
Research
Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning
Research