Awesome Papers

Trending now

#1Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data5.84
#2Helios: Real Real-Time Long Video Generation Model4.92
#3KBLaM: Knowledge Base augmented Language Model2.26
#4ActionParty: Multi-Subject Action Binding in Generative Video Games2.05
#5WildDet3D: Scaling Promptable 3D Detection in the Wild1.29
#6DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning0.00
#7MetaToolAgent: Towards Generalizable Tool Usage in LLMs through Meta-Learning0.00
#8Gradient-Enhanced Partitioned Gaussian Processes for Real-Time Quadrotor Dynamics Modeling0.00
#9Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification0.00
#10Computable Bernstein Certificates for Cross-Fitted Clipped Covariance Estimation0.00
#11BFS-PO: Best-First Search for Large Reasoning Models0.00
#12Efficient Logistic Regression with Mixture of Sigmoids0.00
#13ARM: Advantage Reward Modeling for Long-Horizon Manipulation0.00
#14UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees0.00
#15Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments0.00
#16RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation0.00
#17Sci-Reasoning: A Dataset Decoding AI Innovation Patterns0.00
#18Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs0.00
#19RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction0.00
#20Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?0.00
#21Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain0.00
#22DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents0.00
#23WorldBench: Disambiguating Physics for Diagnostic Evaluation of World Models0.00
#24MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods0.00
#25DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation0.00
#26Context Compression via Explicit Information Transmission0.00
#27Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay0.00
#28VecGlypher: Unified Vector Glyph Generation with Language Models0.00
#29Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation0.00
#30Phi-4-reasoning-vision-15B Technical Report0.00
#314DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video0.00
#32Automatic Generation of High-Performance RL Environments0.00
#33DVD: Deterministic Video Depth Estimation with Generative Priors0.00
#34Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models0.00
#35AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation0.00
#36FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios0.00
#37Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video0.00
#38EXAONE 4.5 Technical Report0.00
#39Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?0.00
#40Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations0.00
#41Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence0.00
#42MultiWorld: Scalable Multi-Agent Multi-View Video World Models0.00
#43Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains0.00
#44Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models0.00
#45Instruction-Guided Poetry Generation in Arabic and Its Dialects0.00
#46Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows0.00
#47LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues0.00
#48PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution0.00
#49PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World0.00
#50Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning0.00