The index · 60
Topics
Discovered by clustering paper embeddings rather than assigned by hand, so the names read like the papers, not like a catalogue.
- Minimax Regret BoundsPapers deriving tight regret bounds and complexity analysis for learning algorithms, focusing on minimax-optimal convergence rates and dimension-dependent lower bounds.44 papersboundexactregretbounds−100%
- Multimodal Video UnderstandingPapers on evaluating and benchmarking multimodal models' ability to understand, generate, and edit video content by integrating visual, textual, and physical reasoning.40 papersvideoeditingstreamingmodalities−100%
- Action-Conditioned World ModelsPapers on learning and using world models that predict environment dynamics conditioned on robot or agent actions for planning and embodied task execution.29 papersactionworldactionsworld models−100%
- Medical Image SegmentationPapers on segmenting anatomical structures and pathological lesions in medical images (CT, MRI, ultrasound) using deep learning and specialized architectures.23 paperssegmentationdicectlesion−100%
- LLM Agent AuditingPapers on verifying the trustworthiness and correctness of LLM-based autonomous agents through tracing, benchmarking, and auditing their reasoning and actions in real-world deployments.21 paperstimeseriesagentsllm agentsverdict−100%
- 3D Gaussian Scene ReconstructionPapers using Gaussian splatting and 3D representations to reconstruct scenes, objects, and surfaces from images, depth, or point cloud data.20 papersgaussian3dcamerareconstruction−100%
- Reward Modeling and Preference LearningPapers on training reward models and critics to learn human preferences through reinforcement learning, including approaches for visual reasoning, multi-objective alignment, and preference-based optimization.18 papersrewardpreferencecriticreinforcement learning−100%
- LLM Cognitive ModelingPapers examining how large language models represent and process belief states, moral reasoning, and conversational understanding—comparing their cognitive representations to human mental models.18 papersmoralconceptualconversationpython−100%
- On-Policy Self-DistillationPapers on training models to distill their own knowledge during on-policy learning, where a model learns from its own generated reasoning or behaviors without requiring a separate teacher network.16 papersonpolicyopsdstudentselfdistillation−100%
- LLM Judge ReliabilityPapers examining biases, artifacts, and consistency issues when using large language models as evaluators for text quality, ranking decisions, and comparative judgments.16 papersranking qualityjudgmentsmetadatasycophancy−100%
- Aesthetic Composition EvaluationPapers examining how to measure, audit, and computationally understand aesthetic and compositional properties in music, visual design, and artwork through machine perception and vision-language models.16 papersmusicaestheticcompositionalaigenerated−100%
- Visual Token PruningPapers on reducing computational costs in vision-language models by selectively pruning or compressing visual tokens through attention mechanisms and encoder optimization.15 paperstokenstokenvisual tokenpruning−100%
- Physics-Informed Operator LearningPapers on using neural networks to learn and approximate differential operators and PDE solutions by incorporating physical constraints and domain knowledge into the learning process.15 papersoperatorphysicsinformedkoopmanoperators−100%
- LLM Security VulnerabilitiesPapers on detecting, evaluating, and mitigating security threats in large language models, including prompt injection attacks, skill extraction, and safety failures through red-teaming and fuzzing approaches.14 paperssecurityskillsmaliciousskill−100%
- Fairness Audits And DebiasingPapers on detecting and mitigating demographic bias in machine learning systems through auditing methods, counterfactual testing, and fairness-aware filtering or adjustments for confounding variables.14 papersfairnessnodefairnessawareaudits−100%
- Accountability in LLM-Assisted WorkPapers addressing traceability, attribution, and responsibility concerns in LLM-assisted workflows including financial analysis, systematic reviews, and citation tracking.13 papersprovenancefinancialinvestmentreview−100%
- Molecular Foundation ModelsPapers applying foundation models and deep learning to predict molecular properties, chemical reactions, and materials structures, leveraging transfer learning and multi-modal representations.13 papersreactionmolecularquantummultispectral−100%
- Weather Forecasting with Machine LearningPapers applying deep learning and ensemble methods to predict weather phenomena like precipitation, temperature, and atmospheric profiles at various timescales.13 papersweatherforecastforecastingclimate−100%
- Federated Learning CommunicationPapers addressing the communication efficiency, privacy preservation, and distributed coordination challenges in federated learning systems across decentralized clients and wireless networks.13 papersdecentralizedfederatedcommunicationwireless−100%
- RAG Reliability and Failure ModesPapers addressing limitations and failure cases of retrieval-augmented generation systems, including hallucinations, misinformation, biases, and methods to improve answer reliability through better retrieval and reasoning strategies.13 papersragretrievalaugmented generationretrievalaugmentedgeneration rag−100%
- Formal Theorem ProvingPapers on using language models with reinforcement learning and symbolic reasoning to automatically prove mathematical theorems and verify formal systems.12 papersproofformaltheoremsymbolic−100%
- Adversarial Robustness in Mixture-of-ExpertsPapers addressing security vulnerabilities and defenses in mixture-of-experts models, including backdoor attacks, adversarial attacks, bit-flip attacks, and watermarking for protection and integrity verification.12 papersbackdoorattackmoeexperts−100%
- KV Cache and Inference EfficiencyPapers on reducing memory and computational overhead during inference through KV cache optimization, prefix caching, and efficient decoding strategies for language and protein models.12 papersproteinprefixslidingsae−100%
- Multimodal Medical Signal FusionPapers on integrating multiple physiological signals (ECG, PPG, EHR) and medical imaging modalities to improve clinical predictions under missing data and signal degradation, with emphasis on survival and treatment outcome estimation.12 papersevaluatorsurvivalmissingnessmortality−100%
- Multi-Agent LLM RoutingPapers on routing and orchestration strategies for directing tasks across multiple LLM agents in online, multi-step workflows, including adaptive delegation and real-time scheduling.11 papersroutingprompt optimizationmultiagent llmonline−100%
- Plant Stress Remote SensingPapers on detecting and monitoring plant health and environmental stress using aerial imagery, spectral measurements, and temporal sensor data from remote sensing platforms.11 papersimageryplantenvironmentalstress−100%
- Cooperative Vehicle PredictionPapers on predicting and optimizing traffic flow through multi-agent modeling of vehicle interactions, collective behavior, and autonomous driving coordination in shared corridors and intersections.11 paperstrafficvehicledrivingcollective−100%
- Agent Skill EvolutionPapers on building and evolving reusable skill libraries that enable agents to handle long-horizon tasks through persistent knowledge and skill composition.10 papersskillskillsskill evolutionreusable−100%
- Automatic Speech RecognitionPapers on building, evaluating, and improving systems for converting spoken audio to text across diverse languages, domains, and acoustic conditions.10 papersspeechasrspeech recognitionvoice−100%
- Non-Standard Text RecognitionPapers on optical and computational recognition of text in non-standard formats including historical manuscripts, sign language, Braille, and ancient scripts.10 papersocrrecognitionspottingsign−100%
- Agent Harness EvolutionPapers on designing and iteratively improving test harnesses and evaluation frameworks that guide agent behavior and performance in coding and operational tasks.10 papersharnessharnessesrepositoriesspend−100%
- Low-Rank Continual LearningPapers on applying low-rank adaptation methods like LoRA to continual learning scenarios where models must learn new tasks sequentially while preserving learned knowledge through efficient parameter updates.10 paperscontinual learningcontinualloralowrank−100%
- Diffusion-Based Inverse ImagingPapers using diffusion models and equivariant neural networks to solve ill-posed inverse problems in imaging and physical field reconstruction with learned or adaptive regularization.9 papersinverse probleminverseregularisationpca−100%
- LLM Compression via Quantization and PruningPapers on reducing model size and computational cost through quantization (including low-bit formats like 4-bit), pruning, and second-order optimization methods like Kronecker-factored Hessians applied to large language models.9 papersquantizationpruningactivationblocks−100%
- Causal Recommendation SystemsPapers applying causal inference methods to optimize recommendations and forecasting in e-commerce and retail, addressing confounding and estimating treatment effects at the product or item level.9 papersrecommendationproductecommerceretail−100%
- Morphology-Aware Language ModelsPapers on incorporating morphological structure and positional awareness into pre-trained models, particularly for morphologically rich and low-resource languages.9 papersturkishparsingpositionalmorphologically−100%
- AI-Generated Text DetectionPapers on methods and challenges for detecting machine-generated text, including authorship attribution, robustness to confounds, and spectral or linguistic signatures that distinguish AI-written content from human writing.8 papersaigeneratedwritingtextdelay−100%
- Multimodal Retrieval EmbeddingsPapers on learning unified embedding representations across modalities (image, text, audio) to enable cross-modal retrieval and matching without task-specific training.8 papersmultimodal retrievalmultivectorretrievaltextguided−100%
- Multilingual TokenizationPapers investigating how tokenizers handle phonetic, orthographic, and linguistic properties across languages, and how tokenization choices affect cross-lingual alignment and representation learning.8 paperscrosslingualtokenizerwordphonetic−100%
- Diffusion Language Model DecodingPapers on accelerating and improving inference in diffusion-based language models through techniques like speculative decoding, rejection sampling, and length-aware token generation to mitigate repetition and degeneration.8 papersdecodingrejectiondiffusion languagelength−100%
- Deformable Multimodal Object DetectionPapers on detecting objects across multiple views, scales, or sensor modalities using deformable networks and fusion techniques, including challenging domains like underwater, maritime, and panoramic scenarios.8 papersobject detectiondeformableobjectwake−100%
- Medical Vision-Language CalibrationPapers on evaluating and improving the reliability and calibration of vision-language models applied to medical imaging, pathology, and visual question answering tasks.7 paperspathologymedicalcalibrationindomain−100%
- Uncertainty-Guided Score-Based InferencePapers combining score-based methods with uncertainty quantification and conformal risk control to improve predictions on stochastic dynamical systems and physical fields using unbiased gradient estimation.7 paperslikelihoodunbiasedphysical fieldsuncertaintyguided−100%
- LLM-Driven Hardware Design AutomationPapers on using large language models and AI agents to automate and accelerate hardware design workflows, from chip accelerators to microarchitecture exploration and neuromorphic systems.7 papershardwaredesignautomationaccelerator−100%
- Activation Vector SteeringPapers on controlling LLM behavior by manipulating learned directions or vectors in activation space without modifying model weights.7 papersrefusalsteeringreflectiondirection−100%
- AI Agent Governance PrimitivesPapers on runtime control mechanisms, identity verification, and organizational enforcement frameworks for managing autonomous AI agents in production deployments.7 papersgovernanceenforcementprimitivesai agents−100%
- Document Grounding and ReviewPapers on evaluating and aligning language models against structured reference documents, whether through model cards, benchmark datasets, or rule-based review of domain-specific documentation.7 papersmodel cardscardsdocumentdocuments−100%
- Text-Attributed Graph LearningPapers on applying graph neural networks to graphs where nodes have text features or descriptions, addressing how to effectively integrate textual information with graph structure in learning tasks.6 papersgraphgnnsgraph neuralcc−100%
- Clinical Guideline AdherencePapers evaluating how well language models follow clinical decision guidelines and protocols when making medical diagnoses and treatment recommendations.6 papersclinicalguidelinesmedicalphenotypes−100%
- Agent Memory ManagementPapers on designing and optimizing memory systems for AI agents, focusing on long-term context retention, personalized storage, and query-aware retrieval to support collaborative and multi-modal agent interactions.6 papersmemoryworking memoryworkingagent memory−100%
- Concept-Based Model ExplanationsPapers on interpreting neural network predictions through human-understandable concepts and counterfactual explanations, with applications to time series and multimodal domains.6 papersexplanationsexplainabilitysynergyexplanation−100%
- Post-Training Circuit AdaptationPapers on modifying and understanding neural circuits during post-training and fine-tuning through targeted adaptation techniques and behavioral circuit analysis.6 papersposttrainingminingcircuitcircuits−100%
- Mental Health BenchmarkingPapers creating and evaluating benchmarks specifically designed to assess language models and AI agents on mental health and psychological tasks, including longitudinal monitoring and conversational assessment.6 papersmentalhealthlongitudinalprevalence−100%
- LLM-Driven Scientific WorkflowsPapers on using large language models as autonomous agents to design, execute, and iterate through scientific workflows including protein folding, control systems, and experimental automation.5 paperstechnologicalscienceexecutable codeprotein−100%
- Discrete Choice PlanningPapers combining discrete choice modeling with planning and trajectory prediction, bridging behavioral learning from user preferences or demonstrations with goal-directed decision-making in navigation and navigation tasks.5 paperschoicecrowddiscretepropagating−100%
- Open-Vocabulary Scene SegmentationPapers on segmenting scenes and objects using open-vocabulary models, foundation models, and generative approaches to enable zero-shot or training-free segmentation across diverse visual domains including LiDAR, UAV imagery, and cluttered environments.5 paperslidarsamsegmentationscene−100%
- Event-Based Vision ProcessingPapers applying event-based cameras (neuromorphic sensors that capture asynchronous pixel-level changes) to video understanding tasks like anomaly detection, object discovery, and reflection removal.5 paperseventeventbasedblurdecay−100%
- Knowledge Graph Question AnsweringPapers on retrieving answers from knowledge graphs through multi-hop reasoning over entities and subgraphs, with focus on integration with retrieval-augmented generation systems.5 papersknowledge graphsubgraphknowledgemultihop−100%
- Medical Image Super-ResolutionPapers on enhancing resolution and reconstruction quality of brain imaging modalities (MRI, EEG, CT) while preserving or recovering fine anatomical details like white-matter lesions.5 paperslesions4xacquiredbrain−100%
- Knowledge Injection And UnlearningPapers on selectively inserting, editing, or removing specific knowledge from language models while preserving existing capabilities and generalization.5 papersactive learninggrainforgetdeletion−100%