When Optimization Becomes Manipulation: Defending Generative Search against Malicious Gen…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Counterexamples as Feedback for Agent Self-Correction
ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box…
X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised D…
A Computationally Feasible Framework for Causal Probabilistic Explanation
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generatio…
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Dec…
Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Gro…
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hy…
Environment Evolution for Terminal Agents
FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Predicti…
Instruction Duplication as an Inference-Time Control Primitive
Spurious Advantage Hidden in GRPO
InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimoda…
Interface-Induced Trajectory Censoring
More Criticism Does Not Make a Better Review: EquiReview-R
Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
Grammar-Aligned Decoding
The Dually Flat Geometry of Planning as Inference
Lose the Order, Keep the Hierarchy: Deordering HTN Plans
Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence
Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding
Representational alignment yields generalizable safety in language models
Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations
Bioinfoysis Technical Report