Google · 61 records

dateidtitleauthorsvenue↑
2026-11-192611.22673FVScore: Specification-Driven Neuro-Symbolic Video EvaluationDo Xuan Long et al.arXiv4
2026-11-132611.18856Self-Improvement Memory Enables Continual Recursive Self-ImprovementXin Yu et al.arXiv31
2026-11-062611.08376Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter ReadoutTushaar Gangavarapu et al.arXiv8
2026-11-052611.08452ReproBridge: Building Reproducibility into ML Research ArtifactsYubo Wang et al.arXiv31
2026-10-272610.37364EmbeddingGemma 2: Unified and Efficient Multimodal RepresentationsHenrique Schechter Vera et al.arXiv30
2026-10-272610.34654Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM AgentsNghi D. Q. BuiarXiv14
2026-10-262610.34662StreamVibe: Proactive Video Agents for Evolving User IntentChengzhi Liu et al.arXiv95
2026-10-232610.32770On-Policy Self-Training: Data-Free Self-Improvement in Large Language ModelsLeon Sick et al.arXiv45
2026-10-222610.19376DeLoop: Repeated Actions as Self-Supervision for Long-Horizon AgentsTianle Chen et al.arXiv21
2026-10-212610.27327Unsupervised Tool Evolution for Coding Agents in Data-Lake AnalyticsYuqing Yang et al.arXiv10
2026-10-192610.17184DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation BottleneckShubham Agarwal et al.arXiv16
2026-10-152610.19128CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation PipelineYuxiang Lai et al.arXiv33
2026-10-142610.14224Harness^2: Recursive Agent Harnessing for an Open WorldRuiyao Xu et al.arXiv84
2026-10-132610.09326VIS-Ground: Video Interactive Storytelling with Contextual GroundingBingxuan Li et al.arXiv43
2026-10-092610.03858Retrieval-Centric Deep Learning in Growing Nonparametric Neural NetworksMaximilian Schlegel et al.arXiv12
2026-10-062610.04109SEER: Self-Evolving Event Reasoning and Retrieval for Time Series ForecastingMingtian Tan et al.arXiv25
2026-10-062610.04137Dynamic Harness Search: Building Multi-Agent Systems Per-Query via PredictionSom Sagar et al.arXiv10
2026-10-052610.00972VeriHarness: Scaling Agentic Verification for Long-Horizon TasksCaiqi Zhang et al.arXiv27
2026-10-052609.32182KeyRec: Bounded Visual Memory for Streaming and Long-Video UnderstandingZihan Chen et al.arXiv6
2026-10-022610.00964RPTune: Learned Context Curation for LLM Catalog SearchChuxuan Hu et al.arXiv20
2026-10-012609.38445AIM: Agentic Idea Management for Automated ResearchHyeong Kyu Choi et al.arXiv32
2026-10-012609.38142AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-DistillationRishabh Agrawal et al.arXiv12
2026-09-302609.37959TabFM: A Zero-Shot Foundation Model for Tabular DataWeihao Kong et al.arXiv17
2026-09-302609.36139Language Models Are "Insecure" ReportersJenny Y. Huang et al.arXiv13
2026-09-302609.37989TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation ModelsDeqing Fu et al.arXiv11
2026-09-302609.36199PreviewDiff: Multimodal Critic-Guided Search over Diffusion LatentsVighnesh Subramaniam et al.arXiv5
2026-09-292609.33780Selecting Diverse SFT Traces Improves Post-RL GeneralizationDylan Zhang et al.arXiv36
2026-09-222609.24972RRSI: Regularized Recursive Self-Improvement of Agent HarnessesPeng Xia et al.arXiv173
2026-09-182609.17496Verifiable Social Reasoning for LLM AssistantsAmir Taubenfeld et al.arXiv43
2026-09-152609.14858Dream-RSI: Recursive Self-Improvement through Evolving WorldsTong Zheng et al.arXiv148
2026-09-152609.15078Enabling Creative Exploration for Vibe Design AgentsYifan Zhang et al.arXiv9
2026-09-092609.09153Procedural Graphs: Self-Evolving Execution Structures for LLM AgentsYuxing Lu et al.arXiv26
2026-09-072609.04523MaxKernel: Agentic Kernel Generation for TPUsShangkun Wang et al.arXiv17
2026-09-012608.30241PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human FeedbackXueqing Wu et al.arXiv12
2026-08-282608.27454WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill EvolutionLiyan Tang et al.arXiv37
2026-08-212608.19880EnvHarness: Awakening Static Worlds for Agent LearningChengsong Huang et al.arXiv109
2026-08-132608.11367Gaze Target Estimation Anywhere with ConceptsXu Cao et al.arXiv5
2026-08-102608.06640Characterizing the Quality Profile of AI-Generated C++ in ProductionMichael Tran et al.arXiv10
2026-07-282607.23687GNM Head: A Generative aNthropometric Model of the human headStylianos Ploumpis et al.arXiv6
2026-07-172607.13188Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump ProcessesMinh-Quan Le et al.arXiv26
2026-07-082607.02770Gemma 4 Technical ReportGemma Team et al.arXiv78
2026-07-082607.02515PointDiT: Pixel-Space Diffusion for Monocular Geometry EstimationHaofei Xu et al.arXiv19
2026-07-012606.32032Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMsGabrielle Kaili-May Liu et al.arXiv28
2026-06-292606.28277Towards Automating Scientific Review with Google's Paper Assistant ToolRajesh Jayaram et al.arXiv10
2026-06-242606.24876FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene GenerationOrest Kupyn et al.arXiv26
2026-06-162602.21103Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient ReasoningSanket Badhe et al.arXiv8
2026-06-152606.12683From AGI to ASITim Genewein et al.arXiv39
2026-06-032606.03979Language Models Need Sleep: Learning to Self-Modify and Consolidate MemoriesAli Behrouz et al.arXiv28
2026-06-022605.30126PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language UnderstandingSelim Kuzucu et al.arXiv8
2026-05-282605.26340ScientistOne: Towards Human-Level Autonomous Research via Chain-of-EvidenceRui Meng et al.arXiv34
2026-05-272605.27295Gemini Embedding 2: A Native Multimodal Embedding Model from GeminiMadhuri Shanbhogue et al.arXiv19
2026-05-222605.22809Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous DrivingJiahao Wang et al.arXiv26
2026-05-152605.14454LiSA: Lifelong Safety Adaptation via Conservative Policy InductionMinbeom Kim et al.arXiv4
2026-05-142605.12587TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingJisu Nam et al.arXiv36
2026-05-132605.10899RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable RewardsGaotang Li et al.arXiv56
2026-05-112605.08083LLMs Improving LLMs: Agentic Discovery for Test-Time ScalingTong Zheng et al.arXiv70
2026-05-112605.06924A^2RD: Agentic Autoregressive Diffusion for Long Video ConsistencyDo Xuan Long et al.arXiv15
2026-05-112605.07039PACEvolve++: Improving Test-time Learning for Evolutionary Search AgentsMinghao Yan et al.arXiv5
2026-05-112605.00933CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised PretrainingHada Melino Muhammad et al.arXiv1
2026-05-062604.25907How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss ContinuumChu-Cheng Lin et al.arXiv2
2026-05-052605.01428Hallucinations Undermine Trust; Metacognition is a Way ForwardGal Yona et al.arXiv23