HuggingFace
JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making
Repeated event forecasting requires extracting predictive signals from noisy evidence and evaluating their value acro...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification
Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and...
HuggingFace
KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
KANLab is a browser-based visualization tool designed to interactively teach the core concepts of Kolmogorov-Arnold N...
HuggingFace
FLORA: An Open Model Suite for Scaling Robotics Data Engines
The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for m...
HuggingFace
On the Token Collapse Phenomenon in Textual Graph Soft Prompting
Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural n...
HuggingFace
Judging the Justification: Decision Certificate Supervision for Generative Reward Models
Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct...
HuggingFace
Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection
In joint-embedding predictive architectures (JEPA), an encoder and a predictor are trained together to produce a repr...
HuggingFace
Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions? For solving ...
HuggingFace
How Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication
Biometric authentication systems increasingly use privacy-preserving mechanisms to protect sensitive templates. Howev...
arXiv
PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets
This work introduces PoKER, a novel probabilistic model engineered to optimize missile launch effectiveness in air-to...
arXiv
Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery
Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned ...
arXiv
From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI
This paper proposes a five-level organization of message formation and understanding within thinking and activity in ...