MMODELYST
Literature

Papers

Showing 1,201–1,300 of 1,326 notable papers
PaperTopicAuthorsPublishedHF ▲
Attacks on Machine-Text Detectors Retain Stylistic FingerprintsVision & multimodalRafael Rivera Soto +2Jun 8, 20262
Squeeze-Release: Iterative Pruning with Exact Structural MinimizationEfficiency & systemsRoman Denkin +3Jun 12, 20262
Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM StatisticsVision & multimodalIgor ItkinJun 10, 20262
ActiveMimic: Egocentric Video Pretraining with Active PerceptionRoboticsXingyao Lin +6Jun 4, 20262
FVSpec: Real-World Property-Based Tests as Lean ChallengesAgentsQuinn Dougherty +3May 31, 20262
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic LanguagesVision & multimodalTanmoy Kanti Halder +4Jun 11, 20262
WebChallenger: A Reliable and Efficient Generalist Web AgentVision & multimodalJayoo Hwang +2Jun 9, 20262
The Cold-Start Safety Gap in LLM AgentsAgentsChung-En Sun +2Jun 5, 20262
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMsAgentsAshutosh Hathidara +3Jun 4, 20262
Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language ModelsCodeChangyue Wang +7Jun 10, 20262
Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang MalayEfficiency & systemsJoanito Agili Lopo +2Jun 10, 20262
Towards Diverse Scientific Hypothesis Search with Large Language ModelsScience & bioHaorui Wang +9Jun 9, 20262
FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow MatchingImage & video genDanilo Danese +4Jun 8, 20262
Can Generalist Agents Automate Data Curation?Vision & multimodalFeiyang Kang +7Jun 2, 20262
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning ModelsSafety & alignmentSai Kartheek Reddy Kasu +2Jun 9, 20262
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on OverleafAgentsJiarui Liu +19Jun 7, 20262
OASIS: From Simulation Data Collection to Real-World Humanoid Loco-ManipulationRoboticsZehao Yu +6Jun 7, 20262
Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation PathSpeech & audioThomas Sesmat +2Jun 5, 20262
TBD-VLA: Temporal Block Diffusion Vision Language Action ModelRoboticsSung-Wook Lee +2Jun 5, 20262
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy DistillationImage & video genXingyu Su +8Jun 4, 20262
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge DistillationEfficiency & systemsMaxime Griot +2Jun 4, 20262
LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language ModelsAgentsPrateek Kumar SikdarJun 1, 20262
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy LearningImage & video genZiyang Yao +12Jun 4, 20262
Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online DiscussionsVision & multimodalXinnong Zhang +4Jun 4, 20262
Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and RecombinationCodeJiasheng Zheng +8May 29, 20262
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language ModelsVision & multimodalDing Zhang +5Jun 2, 20262
Unlocking Feature Learning in Gated Delta Networks at ScaleLLMs & reasoningYifeng Liu +1Jun 2, 20262
Score-Control for Hallucination Reduction in Diffusion ModelsSpeech & audioMahesh Bhosale +5May 29, 20262
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual MisinformationVision & multimodalJunxiao Yang +6Jun 2, 20262
AgentCL: Toward Rigorous Evaluation of Continual Learning in Language AgentsAgentsYiheng Shu +5Jun 2, 20262
BA-T: An Iterative Transformer for Two-View Bundle AdjustmentCodeGanlin Zhang +3Jun 2, 20262
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive RepresentationsVision & multimodalSachin KumarMay 27, 20262
Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language ModelsVision & multimodalGuangzhao He +3Jun 1, 20262
ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and FormatsVision & multimodalShangpin Peng +12May 31, 20262
Confidence-Adaptive SwiGLU for Mixture-of-ExpertsCodeShaohua Li +6May 30, 20262
StressDream: Steering Video World Models for Robust Policy Evaluation and ImprovementRoboticsJunwon Seo +8May 29, 20262
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference OptimizationImage & video genZhuohan Liu +3May 27, 20262
Can Predicted Dynamics Exist in the Physical World?Efficiency & systemsBarak OrMay 23, 20262
Guidance Contrastive Token Credit Assignment for Discrete Policy OptimizationImage & video genShufan Li +4May 29, 20262
Light Interaction: Training-Free Inference Acceleration for Interactive Video World ModelsRoboticsJiacheng Lu +5May 29, 20262
The Good, the Bad, and the Ugly of Markov Boundary for Tabular PredictionEfficiency & systemsShu Wan +3May 28, 20262
Discovering Cooperative Pipelines: Autoresearch for Sequential Social DilemmasAgentsVíctor GallegoMay 28, 20262
MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulationImage & video genDongxia Liu +9Apr 8, 20262
Revealing Algorithmic Deductive Circuits for Logical ReasoningLLMs & reasoningPhuong Minh Nguyen +2May 27, 20262
Phone Segmentation and Recognition through Phonological Activation MappingSpeech & audioShikhar Bharadwaj +10Jul 10, 20261
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model FinetuningSafety & alignmentLu Dai +5Jul 9, 20261
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance DetectionVision & multimodalMd. Shakhoyat Rahman Shujon +4Jul 6, 20261
SiamJEPA: On the Role of Siamese Student Encoders in JEPAVision & multimodalMakoto YamadaJul 4, 20261
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World SpeechSpeech & audioYi-Cheng Lin +3Jul 3, 20261
Do Thinking Tokens Help with Safety?Safety & alignmentNarutatsu Ri +2Jun 23, 20261
Plans Don't Persist: Why Context Management Is Load Bearing for LLM AgentsAgentsAman Mehta +1Jun 22, 20261
Forecasting Future Behavior as a Learning TaskEfficiency & systemsMosh Levy +2Jun 9, 20261
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving PlanningVision & multimodalXirui Li +6Jun 23, 20261
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse RepresentationImage & video genHaorui Ji +3Jun 23, 20261
MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State RecoveryAgentsEnze Ma +9Jun 23, 20261
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified ConditionsVision & multimodalYuichi TatenoJun 22, 20261
Improving Text-to-Music Generation with Human Preference RewardsSpeech & audioYonghyun Kim +4Jun 19, 20261
AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM PretrainingCodeJing Ma +2Jun 14, 20261
A Benchmark and Framework for Evaluating Next Action Predictions in SpreadsheetsCodeTejas Agrawal +3Jun 11, 20261
Re-Centering Humans in LLM PersonalizationReinforcement learningLechen Zhang +2Jun 4, 20261
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model SystemsSpeech & audioSajjad KhanJun 15, 20261
The Price of Anarchy in Disaggregated InferenceAgentsAthos GeorgiouJun 11, 20261
The Ghosts of Polymarket: When Off-Chain Matches Meet On-Chain RevertsRoboticsYiming Shen +4Jun 15, 20261
TuneJury: An Open Metric for Improving Music Generation Preference AlignmentSpeech & audioYonghyun Kim +7Jun 15, 20261
Human Universal GraspingRoboticsKevin Yuanbo Wu +7Jun 15, 20261
WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI SynthesisImage & video genDanilo Danese +4Jun 7, 20261
CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive DrivingSpeech & audioYifan WangMay 31, 20261
A Stationary (and Therefore Compatible) Representation is All You NeedCodeNiccolò Biondi +3Jun 10, 20261
PianoKontext: Expressive Performance Rendering from Deadpan ContextSpeech & audioDmitrii GavrilevJun 10, 20261
Leveraging Morphology for Historical Script Metrological AnalysisVision & multimodalMalamatenia Vlachou Efstathiou +3Jun 8, 20261
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task PerformanceVision & multimodalEtienne Casanova +2May 30, 20261
APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge OperationsVision & multimodalSwadhin Pradhan +2Jun 10, 20261
Building Social World Models with Large Language ModelsImage & video genHaofei Yu +3Jun 9, 20261
τ-Rec: A Verifiable Benchmark for Agentic Recommender SystemsAgentsBharath Sivaram Narasimhan +1Jun 8, 20261
When Behavioral Safety Evaluation Fails: A Representation-Level PerspectiveSafety & alignmentEnyi Jiang +3Jun 6, 20261
Hardening Agent Benchmarks with Adversarial Hacker-Fixer LoopsAgentsZiqian Zhong +5Jun 8, 20261
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit AssignmentAgentsYang Tian +7Jun 8, 20261
Chiaroscuro Attention: Spending Compute in the DarkData & benchmarksPrateek Kumar SikdarJun 6, 20261
EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology AbstractsScience & bioDanqin Zhao +3Jun 6, 20261
SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling MatricesEfficiency & systemsErnests Lavrinovics +5Jun 5, 20261
Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their LatentsVision & multimodalXiuYu Zhang +2Jun 4, 20261
Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal DataReinforcement learningXiuYu Zhang +3Jun 3, 20261
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection DefenseVision & multimodalShuhao Zhang +4May 29, 20261
Honest Lying: Understanding Memory Confabulation in Reflexive AgentsAgentsPrakhar Dixit +2May 28, 20261
Pruning and Distilling Mixture-of-Experts into Dense Language ModelsEfficiency & systemsJunhyuck Kim +5May 27, 20261
ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard NegativesSafety & alignmentAarush Sinha +2Jun 5, 20261
Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code CommentsCodeAbdullah Al Mujahid +2Jun 5, 20261
Streaming Video Generation with Streaming Force ControlImage & video genHanhui Wang +5Jun 5, 20261
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical AlgorithmsCodeChong Zhang +4Jun 3, 20261
Parametric Social Identity Injection and Diversification in Public Opinion SimulationAgentsHexi Wang +4Jun 1, 20261
Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic EvaluationSpeech & audioZixuan Jiang +10May 28, 20261
The Distillation Game: Adaptive Attacks & Efficient DefensesCodeYoussef Allouah +3May 21, 20261
Regret Minimization with Adaptive Opponents in Repeated GamesLLMs & reasoningMingyang Liu +3Jun 4, 20261
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM AgentsAgentsYang Li +3Jun 4, 20261
LLM Anonymization Against Agentic Re-IdentificationAgentsZiwen Li +2Jun 1, 20261
Quality-Guided Semi-Supervised Learning for Medical Image SegmentationVision & multimodalKumar Abhishek +1Jun 1, 20261
Multimodal Music Recommendation System using LLMsSpeech & audioSrikar Prabhas Kandagatla +8May 28, 20261
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image EditingImage & video genYixuan Ding +4Apr 16, 20261
SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech EditingSpeech & audioHanlin Zhang +5Jun 3, 20261
Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman LearningEfficiency & systemsKelan Gray +3Jun 3, 20261
← PrevPage 13 of 14Next →