全部OpenAIHugging FaceArXiv AIGoogle AIVentureBeat AIMarkTechPostPragmatic EngineerThe GradientOne Useful ThingCrunchbase NewsTechCrunchGoogle DeepMindMicrosoft ResearchLlamaIndex BlogarXiv cs.AIarXiv cs.LGarXiv cs.CLarXiv cs.CVNature Machine IntelligenceLilian WengAndrej KarpathySebastian RuderBAIR BlogAgile Lab EngineeringGoogle AI BlogMeta NewsroomMIT Tech Review AITechCrunch AIWiredFull-Stack AI EngineerAgentplexa16zSequoia CapitalY CombinatorElad GilTomasz TunguzNot BoringThe GeneralistSimon WillisonSimon Willison NewsletterLatent SpaceImport AIInterconnectsHamel HusainDAIR.AIEnterprise AI GovernanceStratecherySemiAnalysisBenedict EvansX @OpenAIX @claudeaiX @AnthropicAIX @karpathyX @samaX @demishassabisX @DarioAmodeiX @elonmuskX @miramuratiX @ilyasutX @gdbX @AravSrinivasX @arthurmenschX @ClementDelangueX @alexandr_wangX @mustafasuleymanX @ylecunX @geoffreyhintonX @AndrewYNgX @fcholletX @polynoamialX @_jasonweiX @DrJimFanX @rasbtX @lilianwengX @OriolVinyalsMLX @tri_daoX @percyliangX @ch402X @janleikeX @swyxX @simonwX @jeremyphowardX @OfficialLoganKX @svpinoX @SuhailX @emollickX @_akhaliqX @natolambertX @rowancheungX @bilawalsidhuX @Francis_YAO_X @ShunyuYao14X @tqchenmlX @haozhangmlX @GoogleDeepMindX @huggingfaceX @MistralAIX @perplexity_aiX @NVIDIAAIX @xaiX @victor207755822X @deepseek_aiX @bchernyX @Alibaba_QwenX @Kimi_MoonshotX @dotey
65110 条条目 · 106 个活跃源
2026年9月11日
04:00
arXiv cs.LG
Flow Duality and Source Geometry for Categorical Generation
04:00
arXiv cs.LG
Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
04:00
arXiv cs.CV
CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation
04:00
arXiv cs.CV
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
04:00
arXiv cs.CV
Toward Interpretable Multimodal Fusion: Heat Conduction Modeling for Hyperspectral and LiDAR Joint Classification
04:00
arXiv cs.CL
Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
04:00
arXiv cs.CL
Distribution-aware Language Neuron Identification in Multilingual Large Language Models
04:00
arXiv cs.CL
K/V-Cache Interventions Dissociate Representation Alignment from Persona Expression in Decoder-Only Language Models
04:00
arXiv cs.LG
Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning
04:00
arXiv cs.LG
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
04:00
arXiv cs.LG
RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty
04:00
arXiv cs.CV
Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction
04:00
arXiv cs.CL
Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss
04:00
arXiv cs.LG
From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs
04:00
ArXiv AI
SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities
04:00
ArXiv AI
PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
04:00
ArXiv AI
Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
04:00
ArXiv AI
Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
04:00
ArXiv AI
Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees
04:00
ArXiv AI
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
04:00
ArXiv AI
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
04:00
ArXiv AI
Programmable Cellular Automata
04:00
ArXiv AI
Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs
04:00
arXiv cs.AI
Builder, Defender, Breaker: Measurable Independence and Bounded Autonomy When Generative Models Build, Defend and Test Software
04:00
arXiv cs.CV
HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA
04:00
arXiv cs.CV
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions
04:00
arXiv cs.CV
ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation
04:00
arXiv cs.LG
EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression
04:00
arXiv cs.LG
EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale
04:00
arXiv cs.LG
AUC Maximization from Biased Positive-unlabeled Data with Confidence
04:00
arXiv cs.CL
Assessing the Reusability of Public Speech Resources for Low-Resource Languages: A Central Kurdish Case Study
04:00
arXiv cs.CL
ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation
04:00
arXiv cs.CL
Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization
04:00
arXiv cs.CV
LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone Photos
04:00
arXiv cs.CV
UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration
04:00
arXiv cs.CV
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
04:00
arXiv cs.LG
When More Is Not Better: Component Anti-Synergy in a P300 Speller
04:00
arXiv cs.LG
Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation
04:00
arXiv cs.CL
Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers
04:00
arXiv cs.LG
Phases in a class of associative memories via hidden neurons
04:00
arXiv cs.CL
From Repetition to Recognition: Inductive Discovery of Disinformation Narratives
04:00
arXiv cs.CL
Rubric-Aligned Disentangled Evaluation of Human Simultaneous Interpreting
04:00
arXiv cs.CV
CEM-TUDASR: Computationally efficient multi-modality transformer based unsupervised domain adaptive super-resolution approach
04:00
arXiv cs.CV
Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization
04:00
arXiv cs.CV
A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution
04:00
arXiv cs.LG
Thompson Sampling for Non-Monotone Convex Ridge Bandits: Monotonicity Is Not Needed for Polynomial Regret
04:00
arXiv cs.LG
Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
04:00
arXiv cs.LG
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control
04:00
arXiv cs.CL
FlexComp: One Model for Every Ratio in Context Compression
04:00
arXiv cs.CL