Negative Results

Ask about this topic

Momentum

13 papers in the last four weeks, up 8% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 127

All topics
CardsList

  1. Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews

    Jun 22, 2026Advita Rajiv, Kavitha Kothur, Gautham ReddyLarge Language Model BiasSentiment

    John P. Stevens High School, Edison, NJ 08820 · Ford Foundation, New York, NY 10017 · NC State University, Raleigh, NC 27606

  2. NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models

    Jun 21, 2026Yingjie Zhang, Shuai Li, Peng WangOut-Of-Distribution DetectionOpen-Vocabulary Object Detection

    Northwestern Polytechnical University, Xi’An, China

  3. Negative Knowledge as Failure-aware Shared Memory for AutoResearch

    Jun 19, 2026Hanchun WangResearch AutomationScientific Discovery

    Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.

  4. Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining

    Jun 17, 2026Wicaksono Leksono Muhamad, Yunita SariHate Speech DetectionHate Speech

    Mantera Studio · Universitas Gadjah Mada

  5. A Prototypical Signature Approach for Writer-Independent Offline Signature Verification

    Jun 16, 2026Kecia G. de Moura, Robert Sabourin, Rafael M. O. CruzOnline Signature VerificationDistributional Signatures

    École de technologie supérieure – Université du Québec Montreal, Québec, Canada

  6. MoCo-AIS: A Contrastive Learning Framework for Similarity Computation of Vessel Trajectories

    Jun 16, 2026Ruixin Song, Md Mahbub Alam, Zahra Sadeghi +3VesselsAutomatic Identification System

    Dalhousie University Halifax, NS, Canada · Linnaeus University Växjö,, Sweden · University of Sao Paulo Sao Carlos, SP, Brazil

  7. Reasoning Text-to-Video Retrieval for Operating Room Clips via Action-Driven Digital Twins

    Jun 15, 2026Yiqing Shen, Hao Ding, Mathias UnberathFine-Grained Video UnderstandingTemporal Reasoning

    Johns Hopkins University, Baltimore, MD, USA

  8. Conditional Multi-Event Temporal Grounding in Long-Form Video

    Jun 13, 2026Yuanhao Zou, Arthad Kulkarni, Lucas Tonanez +12Video Temporal GroundingTemporal Grounding

    University of Central Florida · 2Qualcomm AI Research

  9. Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering

    Jun 13, 2026Aarav BediData-CurationPerformance Metric

    Department of Mechanical Engineering University of California, Berkeley

  10. Signed Symmetric Quantization for Few-Bit Integers

    Jun 12, 2026Ian Colbert, Eashan Dash, Pablo Monteagudo-Lago +5QuantizerInformation Asymmetry

    AMD

  11. Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

    Jun 10, 2026Sam MaoArtificial Intelligence AlignmentArtificial Intelligence Safety

    New York University | Interactive Media Arts

  12. TOPSIS-RAD: Ranking According to Desires

    Jun 5, 2026Leonardo Fernandes Costa, Helder Gomes Costa, Diogo Lima +1RankingDesiderata

    Universidade Federal Fluminense Rua Passos da Pátria, 156 Niterói, RJ, Brazil, CEP 24.220-045 · Leonardo Sistemas Consultoria LTDA Av. Albert0 Lamego, 405 Campos dos Goytacazes, RJ, 28016-811, Brazil · Rua Passos da Pátria, 156 Niterói, RJ, Brazil, CEP 24.220-045

  13. Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets

    Jun 5, 2026Zhenyu Yang, Zemin Du, Shengsheng Qian +1Zero-Shot Composed Image RetrievalVision Datasets

  14. The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

    Jun 5, 2026Rahul Nair, Chun TaoModel Fine-TuningSmall Large Language Models

  15. Comparing Sentiment Contagion in AI-Agent and Human Social Networks: Evidence from MOLTBOOK

    Jun 4, 2026Elyes Ben chaabane, Savindu Herath, Yash Raj ShresthaSocial MediaArtificial Intelligence Agents

    UNIL · ETH Zurich

  16. Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

    Jun 3, 2026Balthazar Courvoisier, Tristan CazenaveTransformer AttentionTemporal Attention

    Queensfield AI Technologies, Paris, France · LAMSADE, Universit´e Paris Dauphine - PSL, Paris, France

  17. Noisy memory encoding explains negative polarity illusions

    Jun 3, 2026Yuhan Zhang, Edward GibsonNegationSurprisal

    Department of Linguistics, Stanford University · BIO-X Interdisciplinary Biosciences Institute, Stanford University · Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology

  18. A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting

    Jun 2, 2026Peiyan Zhang, Jason XinModel ActivationsHidden States

    Independent Researcher

  19. Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation

    Jun 2, 2026Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg +4Large Language Model HallucinationCode Completion

    University of Illinois Chicago · Microsoft

  20. FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction

    Jun 2, 2026Chang Kong, Yuebing Li, Peng Mo +2Fine-Grained PerceptionData Generation Pipelines

    Shenzhen Polytechnic University, Shenzhen, China · Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong Macao2026 Greater Bay Area, Shenzhen, China · Shenzhen University, China

  21. When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval

    May 31, 2026Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9Negative ResultsLarge Language Model Generation

    Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Huawei Technologies Co., Ltd. Shenzhen, China · City University of Hong Kong Hong Kong SAR, China +4

  22. On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders

    May 29, 2026Elana Simon, Etowah Adams, James ZouSparse Autoencoder FeaturesModel Activations

    1Stanford University · 2Columbia University

  23. How's it going? Reinforcement learning in language models recruits a functional welfare axis

    May 28, 2026Andy Q Han, David J. Chalmers, Pavel IzmailovPost-TrainingNegative Results

    New York University

  24. Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring

    May 28, 2026Youhan Huang, Jiajun Li, Yilin Fang +2Multi--Task LearningSelf-Supervised Vision Transformers

    1Beijing University of Posts and Telecommunications, Beijing, China · 2Beijing University of Chemical Technology, Beijing, China · 3Capital Medical University, Beijing, China

  25. Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation

    May 28, 2026Jungmin Ko, Jungwon Park, Jimyeong Kim +3SuppressionNegative Results

    Interdisciplinary Program in Artificial Intelligence, Seoul National University · Research Institute for Convergence Science, Seoul National University · Daegu Gyeongbuk Institute of Science and Technology +3

  26. ConvMemory: A Lightweight Learned Memory Reranker, a Negative Attribution Result, and a Research-Preview Conflict Editor

    May 27, 2026Taiheng PanConversational MemoryCross-Encoder

    School of Computing and Information Systems University of Melbourne

  27. EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

    May 27, 2026Yunsheng Zeng, Gen Li, Yuwei Miao +8Frictive Policy OptimizationLarge Reasoning Models

    1Baidu Inc.

  28. Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling

    May 26, 2026Yinan Liu, Wenjin Xu, Zhiyuan Zha +2Knowledge Graph CompletionKnowledge Graphs

    Northeastern University Shenyang, China

  29. Neural Autoregressive Control Variates for the Quantum Monte Carlo Sign Problem

    May 26, 2026Bei Qiao, Lei WangMonte CarloSign

    Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China · University of Chinese Academy of Sciences, Beijing 100049, China

  30. Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models

    May 22, 2026Bo Peng, Jie Lu, Guangquan Zhang +1Out-Of-Distribution DetectionNegative Results

    University of Technology Sydney

  31. Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs

    May 21, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuLarge Language Models FailLinguistics

    The University of Hong Kong · Hong Kong, China · Stellaris AI Limited

  32. High Quality Embeddings for Horn Logic Reasoning

    May 19, 2026Yifan Zhang, Yasir White, Dean Clark +4Recursive ReasonerText Embeddings

    Lehigh University, Computer Science and Engineering, 113 Research Dr., Bethlehem, PA, 18015 · Los Angeles Pierce College, Computer Science, 6201 Winnetka Ave, Woodland Hills, CA 91367 · Colorado College, Computer Science, 14 E Cache La Poudre St, Colorado Springs, CO 80903

  33. SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection

    May 19, 2026Sudheer Tubati, Amit GoyalFraud DetectionNegative Results

    Amazon Music Seattle, USA · Amazon Music San Francisco, USA

  34. When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity

    May 19, 2026Samuel Jacob Chacko, James Hugglestone, Chashi Mahiul Islam +1CybersecuritySkills

    Florida State University, Tallahassee, Florida, USA

  35. Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives

    May 19, 2026Junli Wang, Zhihua Hua, Xueyi Liu +7Causality-Aware End-To-End Autonomous DrivingAutonomous Driving

    Institute of Automation, Chinese Academy of Sciences · Xiaomi Embodied Intelligence Team · Fudan University

  36. Learning over Positive and Negative Edges with Contrastive Message Passing

    May 18, 2026Peter Pao-Huang, Charilaos I. Kanatsoulis, Michael Bereket +1Message Passing Neural NetworksGraph Representations

    Department of Computer Science Stanford University · Stanford University

  37. Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification

    May 17, 2026M. Mikail Demir, M. Abdullah CanbazLegal Reasoning TasksMulti-Label Classification

    Department of Information Science and Technology · College of Emergency Preparedness, Homeland Security, and Cybersecurity · University at Albany, SUNY

  38. Explainable AI Isn't Enough! Rethinking Algorithmic Contestability

    May 15, 2026Timo Freiesleben, Kristof Meding, Gunnar KönigExplainable Artificial IntelligenceEthics

    LMU Munich, Germany · Munich Center for Machine Learning (MCML) · Munich Center for Mathematical Philosophy (MCMP) +3

  39. TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection

    May 11, 2026Yifeng Yang, Jubo Feng, Jing Xu +3Out-Of-Distribution DetectionOpen-Vocabulary Object Detection

    Shanghai Jiao Tong University · University of Electronic Science and Technology of China · Shanghai Artificial Intelligence Laboratory +1

  40. Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning

    May 11, 2026Salar Beigzad, Vansh VermaSingular Learning TheoryForward Propagation

    Computer Engineering University of St. Thomas Minnesota, USA

  41. NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

    May 11, 2026Hyundong Jin, Yo-Sub HanConstrained DecodingLarge Language Model Generation

    Yonsei University Seoul, Republic of Korea

  42. Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

    May 8, 2026Meng Zheng, Samhita Marri, Anwesa Choudhuri +6Action GenerationNegative Results

    United Imaging Intelligence, Boston, MA, USA · University of Illinois Urbana-Champaign, Urbana, IL, USA

  43. Negative Before Positive: Asymmetric Valence Processing in Large Language Models

    May 7, 2026Sohan VenkateshMechanistic InterpretabilityNegative Results

    Manipal Institute of Technology Bengaluru

  44. Unintended Negative Impacts of Promotional Language in Patent Evaluation

    May 6, 2026Bingkun Zhao, Chenwei Zhang, Hao PengPatentInterpretive Layer

    Department of Data Science, City University of Hong Kong, Hong Kong SAR, China · Faculty of Education, The University of Hong Kong, Hong Kong SAR, China · Northwestern Institute on Complex Systems, Northwestern University, Evanston, IL, USA

  45. Beyond Known Objects: A Novel Framework for Open-Set Object Detection using Negative-Aware Norm

    May 4, 2026Yuchen Zhang, Yao Lu, Johannes BetzAutonomous DrivingObjects

    TUM School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI)

  46. A Review of the Receiver Operating Characteristic Curve and a Proof About the Area Beneath It

    Apr 30, 2026Steven RedolfiArea Under The Receiver Operating Characteristic CurveProbabilistic Model

  47. Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection

    Apr 28, 2026Jaskirat Sudan, Hashim Ali, Surya Subramani +1Audio Deepfake DetectionWav2Vec

    1CECS, University of Michigan, Dearborn, USA

  48. Fitting Horn DL Ontologies to ABox and Query Examples: A Tale of Simulation Quantifiers and Finite Models

    Apr 28, 2026Marvin Grosser, Carsten LutzOntologyFirst-Order Logic

    Leipzig University · ScaDS.AI Center Dresden/Leipzig

  49. Mining Negative Sequential Patterns to Improve Viral Genomic Feature Representation and Classification

    Apr 28, 2026Wenxi Zhu, Wensheng Gan, Zhenlian QiSirusGenome-Wide Association Study

    College of Information Science and Technology, Jinan University, Guangzhou 510632, China · College of Cyber Security, Jinan University, Guangzhou 510632, China · Guangdong Eco-Engineering Polytechnic, Guangzhou 510520, China

  50. Negative Ontology of True Target for Machine Learning: Towards Evaluation and Learning under Democratic Supervision

    Apr 27, 2026Yongquan YangProcess-Level SupervisionDemocracy

    Institute of Sciences for AI, Chengdu, Sichuan, China

  51. Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B

    Apr 27, 2026Jon-Paul CacioliSelf-ConsistencyVerbalization

    Independent Researcher, Melbourne, Australia

  52. Machine Learning and Deep Learning Models for Short Term Electricity Price Forecasting in Australia's National Electricity Market

    Apr 26, 2026Wei Lu, Jay Wang, Dingli Duan +3Electricity Price ForecastingElectricity Markets

    School of Engineering, Computer & Mathematical Sciences, Auckland University of Technology (AUT), Auckland 1010, New Zealand · Department of Thermal Energy and Power Engineering, Yantai University, Yantai, China · Department of Building Environment and Equipment, School of Civil Engineering, Hefei University of Technology, Hefei, China +1

  53. How English Print Media Frames Human-Elephant Conflicts in India

    Apr 23, 2026Bonala Sai Punith, Salveru Jayati, Garima Shakya +1MediarefSpecies

    Indian Institute of Technology Palakkad, India · University of Birmingham Dubai, United Arab Emirates

  54. Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding

    Apr 22, 2026Yubo Jiang, Yitong An, Xin Yang +7Modality-Specific EncodersObject Hallucination

    School of Astronautics, Beihang University, Beijing 102206, China · Longcat Interaction Team, Meituan, Beijing 100102, China · Tianmushan Laboratory, Beihang University, Hangzhou 311115, China

  55. Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval

    Apr 20, 2026HaeJun Yoo, Yongseop Shin, Insung Lee +2Text-To-AudioEmbedder

    Sogang University

  56. Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions

    Apr 19, 2026Dongwook Lee, Eunwoo Song, Che Hyun Lee +2Negative Results

    1Interdisciplinary Program in Artificial Intelligence, Seoul National University (SNU) · Department of EE, Yonsei University · Department of ECE, SNU +2

  57. Negative Momentum for Convex-Concave Optimization

    Apr 18, 2026Henry Shugart, Shuyi Wang, Jason M. AltschulerConvex OptimizationConvergence

    UPenn · Yale

  58. Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition

    Apr 18, 2026Yiming Wang, Frederick W. B. Li, Jingyun WangOpen-Vocabulary Action RecognitionZero-Shot

    Department of Computer Science, Durham University

  59. Learning Deterministic Finite-State Machines from the Prefixes of a Single String is NP-Complete

    Jan 18, 2026Radu Cosmin Dumitru, Ryo Yoshinaka, Ayumi ShinoharaAutomataNp-Hard

    Delft University of Technology, Delft, Netherlands · Tohoku University, Sendai, Japan

  60. Co-Evolving Agents: Learning from Failures as Hard Negatives

    Nov 27, 2025Yeonsung Jung, Trilok Padhi, Sina Shaham +4Self-Evolving AgentsRecursive Self-Improvement

    KAIST · Georgia State University · Independent Researcher +2