ObserverBench: Testing Mechanistic Estimates for Intervention and Control
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remot…
Spectral Convergence of Random Feature Method in Multiple Dimensions
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Gen…
Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated…
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generatio…
Counterexamples as Feedback for Agent Self-Correction
Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting
X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System
ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised D…
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Dec…
Spurious Advantage Hidden in GRPO
Instruction Duplication as an Inference-Time Control Primitive
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hy…
InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimoda…
Representational alignment yields generalizable safety in language models
FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Predicti…
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Gro…
More Criticism Does Not Make a Better Review: EquiReview-R
Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding
Interface-Induced Trajectory Censoring
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
Lose the Order, Keep the Hierarchy: Deordering HTN Plans