PaperScope
LIVE · 2026-09-03 05:40 UTC

small 13 papers this week · +100% WoW

papers mentioning "small" in title/abstract · 30d window

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1frb100-40 After Two Decades: An Optimality Certificate and a Preregistered Search StudyOnur Uğurlucs.DM2026-09-02
2Language Models Can Control Their Own AttentionNamgyu Ho, Huzama Ahmad, Woosung Koh +3cs.CL2026-09-02
3Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiencyJia-Nan Wang, Zixun Huang, Kairui Li +1stat.ML2026-09-02
#4Door-in-the-Face Requests and Refusal Behaviour in Large Language ModelsTil Jordancs.AI2026-09-02
#5Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph CompletionMd Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara +1cs.LG2026-09-02
#6DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language ModelsYotam Eshel, Guy Hadad, Guy Feigenblat +3cs.LG2026-09-02
#7A computational approach to maximum likelihood thresholds for colored Gaussian graphical modelsRoser Homs, Olga Kuznetsova, Bernadette J. Stolzstat.ML2026-09-02
#8Towards Zero-Shot Transfer Across Embodiments For Driving VLAsCaio Azevedo, Stefano Sabatini, Sascha Hornauer +1cs.CV2026-09-02
#9YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No VerificationQuansheng Hu, Qin Sun, Qiansen Dai +4cs.CV2026-09-02
#10Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime OptimizationBizhe Bai, Jiakang Yuan, Hongming Wu +8cs.CL2026-09-02
#11SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignmentQingyu Meng, Yiwei Zha, Jiahuan Pei +3cs.LG2026-09-02
#12InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language ModelsChengyin Hu, Dingyi Lu, Jiaju Han +5cs.CV2026-09-02
#13Asymmetric Paired-Annotation Learning for Multi-Structure ULF Pediatric Brain MRI SegmentationHa-Hieu Pham, Dang P. M. Cao, Minh Hoang Pham +4cs.CV2026-09-02
#14Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian ModelsPiyush Saocs.LG2026-09-02
#15A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector SearchSajad Faghfoor Maghrebi, Navid Eslami, Niv Dayancs.DB2026-09-02
#16Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization GapNirajan Kunwor, Sanjaya Poudel, Quoc-Huy Trinh +2cs.CV2026-09-02
#17KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship DetectionZhouyuan Huai, Meiqi Wan, Yan Yang +4cs.CV2026-09-02
#18The Dynamics of Continuous Mixture Collapse in Language ModelsAli Backourcs.LG2026-09-02
#19GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric MatchingLu Han, Xiting Sun, Hao Wang +4cs.CV2026-09-02
#20Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange ModelsJayakumar Manoharan, Yamini Sehgaleess.SY2026-09-02
#21Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style PriorChinmay Rao, Efe Ilıcak, Matthias J. P. van Osch +5eess.IV2026-09-02
#22Network-Aware Forecasting on Wireless Access PointsNiloo Bahadori, Swadhin Pradhan, Peiman Aminics.NI2026-09-02
#23RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume CorrelationZixiang Tong, Lehu Bu, Jin Yangcs.CV2026-09-01
#24The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory AgentsJundong Hu, Shekar Ramachandrancs.AI2026-09-01
#25Kirin: Animal Motion Generation from In-the-Wild VideoBrian Nlong Zhao, Zhuoyang Pan, James M. Rehg +2cs.CV2026-09-01
#26Zeta-Lite: A Concurrent, Branchable In-Browser SQL Database for Agentic MemoryGene Zhangcs.DB2026-09-01
#27Reinforcement learning to choose optimizersMartin van der Schelling, Deepesh Toshniwal, Miguel A. Bessacs.NE2026-09-01
#28D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced DataQuan Minh Nguyen, Hoang M. Ngo, Trong Nghia Hoang +1cs.LG2026-09-01
#29Allocate Before You Embed: Adaptive Visual Input Allocation for Video EmbeddingsSong Jin, Zhongtao Jiang, Chenglei Shen +5cs.CV2026-09-01
#30A Study of Conditional Diffusion Models for Open-Loop Control under Dry Friction and StictionEric Aislan Antonelocs.LG2026-09-01
#31Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face ForensicsSejuti Basu, Ashima Sood, Vijay Kumar +1cs.CV2026-09-01
#32Adaptive Critical Token-Aware Retrieval for Repository-Level Code GenerationKefeng Duan, Dewu Zheng, Yanlin Wang +8cs.SE2026-09-01
#33CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?Damien Sileo, Dimitri Kachlercs.CL2026-09-01
#34The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent GloballyJundong Hu, Shekar Ramachandrancs.LG2026-09-01
#35Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMsJingtan Wang, Arun Verma, Xiaoqiang Lin +4cs.CL2026-09-01
#36From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text ClassificationManish Gupta, Chaitanya Giri, Jayasimha Talurcs.CL2026-09-01
#37Knowledge Distillation During Mid-Training Favors Reasoning over Factual RecallJacqueline He, Howard Yen, Shuyue Stella Li +9cs.CL2026-09-01
#38A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation DataAndres F. Monsalve, Hernan A. Moreno, Christian D. Kummerowphysics.ao-ph2026-09-01
#39LatentPress: Context Compression Beyond Text and VisionZhengze Zhou, Hejian Sangcs.LG2026-09-01
#40Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model StudyArpan Kumar Mahapatracs.CR2026-09-01
#41Harness-of-Harness: Multi-Day Autonomous Software Development with Continual ImprovementHaoyang Yan, Min-le Su, Hangfan Zhang +6cs.AI2026-09-01
#42FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-MakingVahid Reza Khazaie, Ahmed Y. Radwan, Shaina Razacs.CV2026-09-01
#43Edge-Girth as a Structural Edge Feature for Graph Neural NetworksLilian Marey, Charlotte Laclaucs.LG2026-09-01
#44HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16cs.SE2026-09-01
#45Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy SearchZhiliang Chen, Sebastian Ament, David Eriksson +3cs.LG2026-09-01
#46Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed OracleAngshul Majumdarcs.LG2026-09-01
#47Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and SearchingJaewoo Park, Minyoung Lee, Sukmin Seo +11cs.RO2026-09-01
#48Accurate Reconstruction of Gas Turbine Blade Geometry Using 3D/2D Rigid Registration and CT View OptimizationHristo Valtchanov, Nicolas Piché, Vladimir Brailovski +3cs.CV2026-09-01
#49Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving CascadesDushyant Rajputcs.AI2026-09-01
#50VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking ModelsZhiqi Huang, Vivek Datla, Zhichao Xu +3cs.CL2026-09-01

all trends · matching is case-insensitive substring after tokenization