HuggingFace
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized langua...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Multi-agent large language model (LLM) systems often rely on verifier and critic agents to suppress hallucinations, b...
HuggingFace
MirrorPPR: Exemplar-Based Portrait Photo Retouching
While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. T...
arXiv
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where sp...
arXiv
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challeng...
arXiv
The Human Creativity Benchmark
Modern AI evaluation frameworks treat evaluator disagreement as noise to be resolved. In creative domains, profession...
arXiv
A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution
Malware classification remains a challenging problem due to its inherent heterogeneity, the presence of packed binari...
arXiv
Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization
Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.g., ground or drone) w...
arXiv
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. ...
arXiv
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agen...
arXiv
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse,...
arXiv
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosi...