Soft Symbol Grounding for Prototypical Concepts
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Information Specialization and Constrained Synthesis in Multi-Agent LLM Forecasting: A Pr…
Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Mod…
GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
TripPattern: A Pattern-based Text Watermarking Method for Large Language Models
EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning
Confidence-Gated Transductive Test Generation for Code Reranking
Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Mu…
Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction
Diffusion Models and Concept Formation
WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation
LifeFuse-Mem: Lifecycle-Aware State Fusion Against Temporary Overwriting for Long-Term Me…
El Agente Quntur: A research collaborator agent for quantum chemistry
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Con…
Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction …
Continuous Learning of Gravity Field Irregularities Around Small Bodies via Neural Hamilt…
Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detecti…
Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents
I Am AdMan: A Pipeline for Automatic Generation of Personalized Advertising Imagery
Implicit Personality Representations in Humans and LLMs
DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense P…
SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy
Class-wise Contribution Estimation via Logit Maximization for Federated Learning
FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking…
OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on M…
The Vienna 4G/5G Drive-Test Dataset
Representation Before Training: A Practical Benchmark for Generative Medical Event Model …