Automated auditing framework for detecting systematic failures in medical image classifiers using multimodal features and slice discovery.
Proposes uncertainty quantification method for multimodal LLMs using incoherence-adjusted semantic volume for reliable deployment.
SenCache: training-free acceleration for diffusion model inference via sensitivity-aware caching of model outputs across timesteps.
Formalizes desiderata showing compositional generalization requires linear, orthogonal representations in vision embedding models.
Proposes training paradigm decoupling local fidelity from long-term coherence for scaling video generation from seconds to minutes.
TimeMAE: self-supervised framework for learning transferable time series representations using decoupled masked autoencoders.
Proposes dispatcher/executor principle for multi-task reinforcement learning that abstracts unnecessary details for better generalization.
Introduces COLA framework for generating sparse counterfactual explanations using optimal transport and Shapley-based attribution methods.
Super-resolution recurrent diffusion model for renewable energy generation under climate change impacts.
Single-sequence uncertainty estimation method for LLMs addressing computational expense of multi-sequence approaches.
Sample complexity analysis for online reinforcement learning in nonlinear continuous state/action spaces.
Mutual information estimation method using diffusion bridge models for improved domain transfer problems.
Novel semantic parallelism approach for efficient MoE model inference via co-scheduling of model and data placement.
Probabilistic neural networks using t-distribution outputs for improved prediction intervals beyond Gaussian assumptions.
Optimization perspective on reward model quality for RLHF, analyzing factors beyond accuracy that make effective teachers.
Domain decomposition approach for neural operators solving PDEs with improved geometry generalization capabilities.
Research on enforcing token sparsity in multimodal LLMs to reduce computational overhead while maintaining accuracy.
Novel attention mechanism and pointer network for parcel pickup route prediction in logistics optimization.
Theoretical research on manifold learning with normalizing flows for Riemannian geometry in high-dimensional data.
Research on feature selection using permutation-invariant embeddings and policy-guided search with generative models.
Lightweight prediction model for LLM-based agentic workflow performance across agent configurations and prompting strategies.
Framework converting multimodal LLM generative capabilities into zero-shot discriminative embedding models without extensive pre-training.
Model merging technique using task vector distillation to improve robustness of multi-task learning across diverse settings.
Theoretically motivated improvement to supervised fine-tuning for LLMs by rectifying reward structure to match RL generalization.
Offline multi-agent reinforcement learning using efficient flow-based policies for time-sensitive deployment.
Framework of strategies for improving LLM-based forecasting by integrating historical data and textual context with reduced computational cost.
Investigation of in-context learning in world models for embodied AI to adapt to novel environmental configurations.
Interpretable time series forecasting method using hierarchical prototypes to explain model decision-making.
Foundation inference model using in-context learning to predict marked temporal point process event sequences across different systems.
Process Reward Models that capture step-by-step reasoning dependencies in LLMs to improve reasoning alignment with final outcomes.
Benchmark dataset of 50 condensed matter theory problems for evaluating LLMs on advanced research-level physics problem-solving.
Permutation-invariant representation learning for privacy-preserving feature selection using generative intelligence.
Carré du champ flow matching: geometry-aware regularization technique for generative models improving quality-generalization tradeoff.
Hybrid tensor-EM method for learning mixtures of linear dynamical systems with improved performance on noisy time-series data.
Evaluation of zero-shot super-resolution capabilities in machine-learned operators for modeling continuous physical phenomena.
ToSFiT: Thompson sampling via LLM fine-tuning for Bayesian optimization in large discrete spaces without acquisition function maximization.
Differential privacy framework for decentralized learning using matrix factorization to enable collaborative training while preserving privacy.
FAPO method for LLM reasoning via reinforcement learning that filters flawed positive rollouts to improve policy optimization with verifiable rewards.
DiffuMamba: diffusion language model with Mamba backbone for efficient masked sequence modeling, achieving linear-time complexity vs Transformer quadratic overhead.
Analysis of stochastic gradient descent-based unlearning algorithms (D2D and R2D) with provable guarantees for removing training data impact.
Multi-agent reinforcement learning approach using attention for automated feature transformation in structured data processing.
Method for monitoring LLM API consistency over time by tracking log probability changes to detect undisclosed model updates.
Study on membership inference attacks for extracting training data from LLMs, demonstrating privacy risks through coordinated extraction and verification techniques.
Generalized Primal Averaging (GPA) optimizer for faster LLM training, extending Nesterov's method and unifying recent averaging-based approaches like DiLoCo.
Trust region masking technique for LLM reinforcement learning to address off-policy divergence in policy gradient training of large language models.
CSyMR benchmark for evaluating LLMs on compositional music information retrieval tasks requiring multi-step reasoning over symbolic music notation.
DUET method for LLM unlearning using distilled teacher models to remove undesirable knowledge efficiently while avoiding catastrophic forgetting.
Federated-inspired batch correction for single-cell RNA sequencing without centralizing high-dimensional datasets.
Position paper proposing agentic framework for time series forecasting with iterative refinement and adaptation.
KV-cache quantization to 2-bit precision enabling long video generation on resource-constrained hardware.