| Posterior Matching Distillationlisted by NVIDIA on Hugging Face |
NVIDIA |
Nov 2026 |
0 |
458 |
| NarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative Decodinglisted by NVIDIA on Hugging Face |
NVIDIA |
Nov 2026 |
0 |
458 |
| Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API FailuresarXiv · authors at Genentech, Inc. |
Genentech, Inc. |
Nov 2026 |
0 |
27 |
| DNeo: Your Parallel Draft Model Needs Better Target Feature Encodinglisted by Cerebras on Hugging Face |
Cerebras |
Nov 2026 |
0 |
132 |
| LLM-Guided Cluster Lifecycle Management: Deciding When and How to Evolve Behavioral ClustersarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Vision-as-a-Tool: Visual Harness for Multimodal Agentic CodingarXiv · authors at Microsoft |
Microsoft |
Nov 2026 |
0 |
129 |
| Zero-SM NCCL: A Systematic Guide to Designing and Deploying SM-Free GPU CommunicationarXiv · authors at NVIDIA |
NVIDIA |
Nov 2026 |
0 |
458 |
| Interpretable weight-space programming builds transparent transformers and brain encoding modelsarXiv · authors at Microsoft |
Microsoft |
Nov 2026 |
0 |
129 |
| Scaling medical imaging report generation with multimodal reinforcement learningNature Communications · authors at Microsoft |
Microsoft |
Nov 2026 |
14 |
129 |
| Compiling Known Rules into Compact Neural Agents: Weight-Space Programming on Unseen GamesarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Benchmarks Don't Talk Back: Learning Through Self-DisagreementarXiv · authors at Microsoft |
Microsoft |
Nov 2026 |
0 |
129 |
| JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Examslisted by Sakana AI on Hugging Face |
Sakana AI |
Nov 2026 |
0 |
26 |
| Advancing Weighted Partial MaxSAT Solving via Differentiable GPU GuidancearXiv · authors at NVIDIA |
NVIDIA |
Nov 2026 |
0 |
458 |
| 78 more papers by Microsoft |
| DecArena: Evaluating Large-Scale Decentralized Multi-Agent CollaborationarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| Vocabulary-Free Next-Event Prediction on Temporal GraphsarXiv · authors at Amazon |
Amazon |
Nov 2026 |
0 |
931 |
| 80 more papers by NVIDIA |
| Back to Pixels: Lifting Latent Video Diffusion into Pixel Spacelisted by Roblox on Hugging Face |
Roblox |
Nov 2026 |
0 |
30 |
| Quantum-walk transport oracles and amplitude estimation of a scalar range statistic in proton therapyarXiv · authors at Samsung Semiconductor |
Samsung Semiconductor |
Nov 2026 |
0 |
13 |
| Beyond Proxy Metrics: MLLMs as Human Surrogates for Explainable AI EvaluationarXiv · authors at Mistral AI |
Mistral AI |
Nov 2026 |
0 |
260 |
| 73 more papers by Amazon |
| MPEG-Diffusion: Mixed-Resolution Video Generationlisted by Roblox on Hugging Face |
Roblox |
Nov 2026 |
0 |
30 |
| Polynomial Denoisers on the Image Manifold: Volterra Networks for Self-Contained Pixel DiffusionarXiv · authors at Samsung Semiconductor |
Samsung Semiconductor |
Nov 2026 |
0 |
13 |
| From Procedures to Permissions: Learning Precise Subagent Authorization from Agent SkillsarXiv · authors at Samsung Semiconductor |
Samsung Semiconductor |
Nov 2026 |
0 |
13 |
| EventHOI: Event-Driven Resource-Efficient Hand-Object Interaction Logging on SmartglassesarXiv · authors at Samsung Semiconductor |
Samsung Semiconductor |
Nov 2026 |
0 |
13 |
| Rethinking Data Selection: The Importance of Coverage over Difficulty in LLM Fine-TuningarXiv · authors at The Allen Institute for Artificial Intelligence |
The Allen Institute for Artificial Intelligence |
Nov 2026 |
1 |
21 |
| The Memory Trap: Language Agents Overgeneralize from Benign InteractionsarXiv · authors at Anthropic |
Anthropic |
Nov 2026 |
1 |
631 |
| TCSExam: Evaluating Frontier LLMs on the Full Range of TCS ResearcharXiv · authors at Moonshot AI |
Moonshot AI |
Nov 2026 |
1 |
108 |
| s$^3$: Simple Scaling of Swarms via Cooperative Multi-agent RLarXiv · authors at The Allen Institute for Artificial Intelligence |
The Allen Institute for Artificial Intelligence |
Nov 2026 |
0 |
21 |
| 41 more papers by Samsung Semiconductor |
| Towards Foundation Decision Models: Drexlisted by Nace AI on Hugging Face |
Nace AI |
Nov 2026 |
0 |
6 |
| Fast verification of fault tolerant magic state preparation circuits with the CNOT + T gate setarXiv · authors at Quantinuum |
Quantinuum |
Nov 2026 |
0 |
3 |
| RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wildlisted by Hugging Face on Hugging Face |
Hugging Face |
Nov 2026 |
0 |
10 |
| Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimizationlisted by Snowflake on Hugging Face |
Snowflake |
Nov 2026 |
0 |
47 |
| Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attentionlisted by Writer on Hugging Face |
Writer |
Nov 2026 |
0 |
46 |
| MEMIG: Self-evolving Memory Construction for Antibody OptimizationarXiv · authors at Genentech, Inc. |
Genentech, Inc. |
Oct 2026 |
0 |
27 |
| SIEVE: Preserving Cross-Image Evidence via Depth-Aware Token CompressionarXiv · authors at DatologyAI |
DatologyAI |
Oct 2026 |
0 |
14 |
| SpBench: An Agent-Native Framework for Cross-Engine Lakehouse BenchmarkingarXiv · authors at Snowflake |
Snowflake |
Oct 2026 |
0 |
47 |
| AVID: A Weakly Aligned RGB-Infrared Dataset and Perturbation Benchmark for Tiny Aerial TargetsarXiv · authors at Hugging Face |
Hugging Face |
Oct 2026 |
1 |
10 |
| Rethinking Pre-pretrainingarXiv · authors at Cohere |
Cohere |
Oct 2026 |
0 |
124 |
| V-CAPE: Visual Consistency Assessment for Product Image EditingarXiv · authors at Faculty |
Faculty |
Oct 2026 |
0 |
91 |
| Agentic Backdoors via Pretraining PoisoningarXiv · authors at Anthropic |
Anthropic |
Oct 2026 |
1 |
631 |
| Persistence, Exposure, and Credit Routing in Linear Temporal Predictive CodingarXiv · authors at Sakana AI |
Sakana AI |
Oct 2026 |
0 |
26 |
| Follow the Gradient: Tracing Safety Degradation Back to Training Datalisted by DatologyAI on Hugging Face |
DatologyAI |
Oct 2026 |
0 |
14 |
| Timestrallisted by Mistral AI on Hugging Face |
Mistral AI |
Oct 2026 |
0 |
260 |
| SEPhIA: spiking electro-photonic integrated tiled architecture leveraging multi-wavelength lasers for scalable optical neuromorphic computingnpj Unconventional Computing · authors at HP |
HP |
Oct 2026 |
3 |
26 |
| Model Organisms of Collusion: Corrective Transfer in Untrusted MonitorsarXiv · authors at Anthropic |
Anthropic |
Oct 2026 |
0 |
631 |
| REGATTA: A Cross-Domain Measurement Framework and Fault-Injection Harness for Enterprise AI AgentsarXiv · authors at (FCRS = US175) Novartis Institutes for BioMedical Research, Inc. |
(FCRS = US175) Novartis Institutes for BioMedical Research, Inc. |
Oct 2026 |
0 |
4 |
| Injection is all you need: parallel universal logic in high-rate concatenated self-dual codesarXiv · authors at Quantinuum |
Quantinuum |
Oct 2026 |
0 |
3 |
| CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Modelslisted by Biohub on Hugging Face |
Biohub |
Oct 2026 |
0 |
17 |
| Evolving Semantic Indexes for Generative RetrievalarXiv · authors at Coupang |
Coupang |
Oct 2026 |
0 |
28 |
| SANE: Automated Scorer-Specific Metamorphic Testing for LLM JudgesarXiv · authors at Anduril |
Anduril |
Oct 2026 |
0 |
2,631 |
| AfriGuard: Safety and Robust Refusal For African LanguagesarXiv · authors at Cohere |
Cohere |
Oct 2026 |
1 |
124 |
| When Should AI Chime In? Benchmarking Timely Contribution of Proactive Agents in Multi-Party ChatarXiv · authors at The Allen Institute for Artificial Intelligence |
The Allen Institute for Artificial Intelligence |
Oct 2026 |
0 |
21 |
| Scaling Vision Foundation Models for Toxicologic PathologyarXiv · authors at (FCRS = US175) Novartis Institutes for BioMedical Research, Inc. |
(FCRS = US175) Novartis Institutes for BioMedical Research, Inc. |
Oct 2026 |
0 |
4 |
| Measurement-efficient energy estimator for quantum chemistry of photodynamic materialsarXiv · authors at Quantinuum |
Quantinuum |
Oct 2026 |
0 |
3 |
| Quantum error correction well below the color code thresholdarXiv · authors at Quantinuum |
Quantinuum |
Oct 2026 |
5 |
3 |
| TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision ModelsarXiv · authors at Hugging Face |
Hugging Face |
Oct 2026 |
1 |
10 |
| HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research AgentsarXiv · listed by Snowflake on Hugging Face |
Snowflake |
Oct 2026 |
0 |
47 |
| Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM InferencearXiv · authors at LG Electronics |
LG Electronics |
Oct 2026 |
0 |
2 |
| 42 more papers by Quantinuum |
| QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversitylisted by Sakana AI on Hugging Face |
Sakana AI |
Oct 2026 |
0 |
26 |
| BenchChecker: Assessing the Credibility of Bug-Fixing Benchmarks for LLMsarXiv · authors at Palo Alto Networks, Inc. |
Palo Alto Networks, Inc. |
Oct 2026 |
0 |
9 |
| Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Linear Projectors Enable?arXiv · authors at Cohere |
Cohere |
Oct 2026 |
0 |
124 |
| What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to InterventionsarXiv · authors at St. Jude Children's Research Hospital, Inc. |
St. Jude Children's Research Hospital, Inc. |
Oct 2026 |
0 |
5 |
| Defence against the dark arts of distillation: Unsupervised discovery of subliminal learningarXiv · authors at Spotify |
Spotify |
Oct 2026 |
1 |
15 |
| TabReliBench: Evaluating Tabular Foundation Models Beyond Predictive AccuracyarXiv · authors at Cerebras |
Cerebras |
Oct 2026 |
1 |
132 |
| Unconstrained CTI-REALM with Open-WeightsarXiv · authors at Mistral AI |
Mistral AI |
Oct 2026 |
0 |
260 |
| EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program EvolutionarXiv · authors at Sakana AI |
Sakana AI |
Oct 2026 |
1 |
26 |
| $σ$Transfer: Uncertainty Transfer from Small to Large Networks under $μ\mathrm{P}$arXiv · authors at Spotify |
Spotify |
Oct 2026 |
0 |
15 |
| Continually Post-training Small Models via Synthetic Self-distillationlisted by LG AI Research on Hugging Face |
LG AI Research |
Oct 2026 |
0 |
35 |
| Probabilistic Sensing, Deterministic Authority: Admitting Model-Produced Observations into Sufficiency-Checked Governance ContractsarXiv · authors at Anthropic |
Anthropic |
Oct 2026 |
0 |
631 |
| A Cyber+Human Data Windfall to Revolutionize Cyberpsychology, Predictive Modeling, and Cyber DefenseComputational Brain & Behavior · authors at LEIDOS, INC. |
LEIDOS, INC. |
Oct 2026 |
1 |
5 |
| 30 more papers by Sakana AI |
| Measurement circuit ansatz: Naimark versus quantum neural-network measurementsQuantum Science and Technology · authors at LG Electronics |
LG Electronics |
Oct 2026 |
0 |
2 |
| Inference and learning in sparse autoencoders as natural gradient flowCold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory) · authors at Astera Institute |
Astera Institute |
Oct 2026 |
0 |
7 |
| 31 more papers by Anthropic |
| The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive ConsolidationarXiv · authors at Mistral AI |
Mistral AI |
Sep 2026 |
0 |
260 |
| How Local Mixing Encodes Relative Position in Global NoPE AttentionarXiv · authors at Zyphra |
Zyphra |
Sep 2026 |
1 |
16 |
| A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?listed by KRAFTON on Hugging Face |
KRAFTON |
Sep 2026 |
0 |
23 |
| What if automating AI R&D triggers an intelligence explosion?arXiv · authors at OpenAI |
OpenAI |
Sep 2026 |
5 |
851 |
| What masking geometry works best for EEG foundation models?listed by Hugging Face on Hugging Face |
Hugging Face |
Sep 2026 |
0 |
10 |
| Aristotle: IMO-level Automated Theorem ProvingSuperIntelligence - Robotics - Safety & Alignment · authors at Harmonic |
Harmonic |
Sep 2026 |
156 |
2 |
| 16 more papers by Hugging Face |
| Performance-portable GPU acceleration of the hybrid particle-in-cell code dHybridRarXiv · authors at Cerebras |
Cerebras |
Sep 2026 |
0 |
132 |
| When Recursive Models Finish ComputingarXiv · authors at Zyphra |
Zyphra |
Sep 2026 |
1 |
16 |
| Robust Fusion of Semantic and Behavioural Signals for LLM Reranking in Personalised SearcharXiv · authors at Spotify |
Spotify |
Sep 2026 |
0 |
15 |
| DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compressionlisted by DeepSeek on Hugging Face |
DeepSeek |
Sep 2026 |
0 |
33 |
| Lightweight, practical encrypted face recognition with GPU supportJournal of Information Security and Applications · authors at LG Electronics |
LG Electronics |
Sep 2026 |
1 |
2 |
| ABDS: Classifying Protocol Divergence Causes via AS-Boundary CorrelationarXiv · authors at Palo Alto Networks, Inc. |
Palo Alto Networks, Inc. |
Sep 2026 |
0 |
9 |
| Benchmarking Hybrid Deep Research Across Database Querying and Web SearcharXiv · authors at Snowflake |
Snowflake |
Sep 2026 |
1 |
47 |
| Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language ReasoningarXiv · listed by Cohere on Hugging Face |
Cohere |
Sep 2026 |
0 |
124 |
| Unlocking Lossless Speedups in LLMs via Discrete DiffusionarXiv · authors at Cerebras |
Cerebras |
Sep 2026 |
7 |
132 |
| 8 more papers by Cerebras |
| Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settingsarXiv · authors at Genentech, Inc. |
Genentech, Inc. |
Sep 2026 |
0 |
27 |
| 34 more papers by Snowflake |
| BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitiveslisted by Roblox on Hugging Face |
Roblox |
Aug 2026 |
0 |
30 |
| WHALE: A Simple Recipe for Joint Harness-Weight Optimizationlisted by KRAFTON on Hugging Face |
KRAFTON |
Aug 2026 |
0 |
23 |
| NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inferencelisted by H Company on Hugging Face |
H Company |
Aug 2026 |
0 |
28 |
| Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge ReconstructionarXiv · authors at Biogen |
Biogen |
Aug 2026 |
0 |
7 |
| Incremental Recommendation via Causal ModelsarXiv · authors at Spotify |
Spotify |
Aug 2026 |
1 |
15 |
| Rapid On-Robot Learning for Dynamic Manipulation Skills: Robot JugglingarXiv · authors at Robotics and AI Institute |
Robotics and AI Institute |
Aug 2026 |
0 |
24 |
| Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic VerificationarXiv · authors at HP |
HP |
Aug 2026 |
0 |
26 |
| A Programming Paradigm for Spatiotemporal ComposabilityarXiv · listed by DeepSeek on Hugging Face |
DeepSeek |
Aug 2026 |
19 |
33 |
| 7 more papers by Spotify |
| Prime Agent: A Self-Improving RLM HarnessarXiv · listed by Prime Intellect on Hugging Face |
Prime Intellect |
Aug 2026 |
28 |
38 |
| From Paper to Pixels: Lessons Learnt from Creating and Using the Nuclear Explosion Legacy Data RepositoryPure and Applied Geophysics · authors at LEIDOS, INC. |
LEIDOS, INC. |
Aug 2026 |
1 |
5 |
| Towards Quantifying Benchmark Optimization in ASR Modelslisted by Hume AI on Hugging Face |
Hume AI |
Aug 2026 |
0 |
5 |
| 9 more papers by Mistral AI |
| Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPIlisted by Prior Labs on Hugging Face |
Prior Labs |
Aug 2026 |
0 |
23 |
| Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly DetectionarXiv · authors at LG Electronics |
LG Electronics |
Aug 2026 |
0 |
2 |
| 30 more papers by Cohere |
| A Dual Evaluation for Music TranscriptionarXiv · authors at The Allen Institute for Artificial Intelligence |
The Allen Institute for Artificial Intelligence |
Aug 2026 |
0 |
21 |
| The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought DynamicsarXiv · authors at St. Jude Children's Research Hospital, Inc. |
St. Jude Children's Research Hospital, Inc. |
Aug 2026 |
1 |
5 |
| K-EXAONE 2.0 Technical Reportlisted by LG AI Research on Hugging Face |
LG AI Research |
Aug 2026 |
0 |
35 |
| AutoLiquid: Autonomic Data Layout Optimization for the Databricks LakehouseProceedings of the VLDB Endowment · authors at Databricks |
Databricks |
Aug 2026 |
1 |
897 |
| Bicycle Acrobatics with Reinforcement LearningarXiv · authors at Robotics and AI Institute |
Robotics and AI Institute |
Aug 2026 |
0 |
24 |
| Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares CertificatesarXiv · authors at OpenAI |
OpenAI |
Jul 2026 |
0 |
851 |