Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion
Research
Research News
New papers, breakthroughs and academic AI research
LSTM-UT and Recurrent-Depth Transformers on Cellular Automata
Research
Why Pretraining Fails to Share Cross-Lingual Knowledge
Research
A frontend-backend architecture for tool calls in full-duplex speech models
Research
Compressed Active Subspaces for Scalable Bayesian Inference
Research
The Role of Fine-grained Harm Signals in LLM Safety
Research
Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery
Research
From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models
Research
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Research
For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances
Research
Rethinking Multi-Agent Collaboration: When More Is Less
Research
Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows
Research