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
Legible Failures: Detecting and Repairing In-Context Binding Errors
04:00
arXiv cs.LG
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
04:00
arXiv cs.CL
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
04:00
arXiv cs.LG
Polyhedral Geometry of Time-to-First-Spike Neural Networks
04:00
arXiv cs.CV
Multi-Modal Controlled Coherent Motion Generation
04:00
arXiv cs.CV
BruNet: A Cross-Domain Transfer Framework for Bruise Segmentation
04:00
arXiv cs.CV
BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
04:00
arXiv cs.CL
The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
04:00
arXiv cs.CL
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
04:00
arXiv cs.LG
A Dynamic Fusion Large Language Model for Traffic Flow Prediction
04:00
arXiv cs.LG
MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
04:00
arXiv cs.CL
RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
04:00
arXiv cs.LG
Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development
04:00
arXiv cs.CV
Pre- and Post-Treatment Brain Metastases Segmentation Using nnU-Net with Post-Processing for BraTS 2026
04:00
arXiv cs.CL
Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs
04:00
arXiv cs.LG
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs
04:00
arXiv cs.CV
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
04:00
arXiv cs.CV
Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation
04:00
arXiv cs.CV
UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound
04:00
arXiv cs.CV
LoopVAE: Recurrent Depth Across Scales for Visual Tokenization
04:00
arXiv cs.CV
Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification
04:00
arXiv cs.CV
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
04:00
arXiv cs.CV
Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates
04:00
arXiv cs.CV
World in World: Explore the World with World Models
04:00
arXiv cs.CV
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
04:00
arXiv cs.LG
Combining Synthetic and Real Data for Low-Resource Historical OCR: A Manchu Case Study
04:00
arXiv cs.LG
DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis
04:00
arXiv cs.LG
Prevalence Determines Precision:Silent Contamination in Detector-Defined Datasets
04:00
arXiv cs.CL
More than half of recent astronomy papers are written with language-model assistance
04:00
arXiv cs.CL
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech
04:00
arXiv cs.CL
Epistemic orientation predicts legislative effectiveness among members of the US Congress
04:00
arXiv cs.CV
OmniKVQuant: KV Cache Quantization for Omni-LLMs
04:00
arXiv cs.LG
Learnware and AI Model Management System
04:00
arXiv cs.LG
Generalized Score Matching for Parameter Estimation on Convex Domains
04:00
arXiv cs.LG
Particle GFlowNets: Rethinking Generative Marginalization Models
04:00
arXiv cs.CL
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
04:00
arXiv cs.CL
The widening evaluation gap in medical large language model research 2023 to 2026
04:00
arXiv cs.CL
Domain-Specific Hallucination Detection in Large Language Models
04:00
arXiv cs.LG
A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph
04:00
arXiv cs.LG
LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy Analytics
04:00
arXiv cs.LG
RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series Imputation
04:00
arXiv cs.CL
Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
04:00
arXiv cs.CL
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
04:00
arXiv cs.CL
Distance generalization in transformers: why bother with positional encoding?
04:00
arXiv cs.LG
Musec: MomentUm SpEctral Clipping for Stable Muon-type Training
04:00
arXiv cs.CL
IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing
04:00
arXiv cs.CV
LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians
04:00
arXiv cs.CV
Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
04:00
arXiv cs.CV
MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities
04:00
arXiv cs.LG