AI
EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
Researchers have developed EgoCITE, a system for indexing and retrieving information from egocentric...
AI
BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
Researchers have developed BrainWAM, a framework that combines semantic reasoning and predictive wor...
AI
Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models
Researchers have developed a method to modify a learned world model's behavior by making targeted ch...
AI
From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents
Researchers have proposed a new framework called RUPA (Relational Uncertainty Propagation for Agents...
AI
Neurosymbolic Embodied Agents
Researchers have developed a neurosymbolic agent that can perform household task...
AI
Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents
Researchers have developed a new attack method called Environment State-Text Inj...
AI
LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization
Researchers have created a new benchmark called LongNovel to detect hallucinatio...
AI
Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives
Researchers evaluated how well both humans and large language models can track e...