Adaptive hybrid model selection framework for demand forecasting across multiple horizons and SKUs.
Flow-based generative model for predicting molecular crystal structures with periodic boundary conditions.
FLoRG enables parameter-efficient federated fine-tuning of LLMs using low-rank adaptation with Procrustes alignment across distributed clients.
Deep learning approach for antibody sequence engineering using phylogenetic models and affinity maturation data.
EMPO² framework combines on/off-policy RL with memory augmentation to improve exploration in LLM agents, addressing novel state discovery limitations.
Web-to-Knowledge-to-Web pipeline iteratively crawling domain-specific sources to discover SME suppliers in specialized industry sectors.
Framework establishing first-order equivalence between activation steering and weight updates for parameter-efficient LLM adaptation.
MatRIS: Foundation machine learning interatomic potentials with equivariant inductive bias for efficient material simulation.
Geometric pretraining approach for protein design combining structure learning and conformational ensembles with rigidity-aware representations.
mlx-vis: Python library implementing GPU-accelerated dimensionality reduction (UMAP, t-SNE, PaCMAP, etc.) on Apple Silicon via MLX.
Method for detecting visual hallucinations in VLM outputs on cartoon character images using pose information.
BInD: Diffusion model for multi-objective structure-based drug design balancing molecular generation with protein interaction requirements.
Philosophical investigation of LLMs' ontological status as agents, analyzing architecture, training, and extensions enabling agent-like behavior.
FALCON: Self-supervised video pretraining for UAV action recognition addressing spatial imbalance in aerial footage with object-centric learning.
Self-supervised seismic data reconstruction method using self-consistency learning for handling irregularly distributed seismic receiver data.
Survey on LLMs transforming scientific research covering literature search, hypothesis generation, experimentation, content generation, and peer review assistance.
Research on adversarial robustness of quantum classifiers using circuit cutting techniques for NISQ-era quantum computing.
Research paper examining governance failures in preventing AI-generated non-consensual intimate images using open-source face-swapping and nudification tools.
Research paper proposing reward modeling with chain-of-thought reasoning for improved LLM alignment with human preferences via reinforcement learning.
Entropic mirror descent optimization algorithm for linear systems with Polyak-type stepsizes and implicit bias analysis including convergence guarantees.
ContextBench: benchmark for generating targeted linguistically fluent inputs that activate specific latent features in language models for safety analysis.
Sysformer: method for safeguarding frozen LLMs using adaptive system prompts to ensure safety compliance without model retraining in deployment scenarios.
SPoT: tokenization strategy for Vision Transformers enabling continuous subpixel token placement instead of grid-based constraints for sparse regime exploitation.
Cross-attention analysis in transformers for interpreting TCR-pMHC binding predictions using TULIP model for understanding immune system mechanisms.
Multi-agent RL framework with student-teacher curriculum for autonomous driving behavior generation addressing complex real-world traffic scenarios and critical situations.
Multivariate fields of experts framework for learning image priors using Moreau envelopes for inverse problems including denoising, deblurring, and MRI reconstruction.
Kernel VICReg: self-supervised learning method operating in reproducing kernel Hilbert space to capture nonlinear dependencies in representation learning.
VEGA: AI agent for electric vehicle routing combining physics-informed neural operators with reinforcement learning for energy-aware charge-conscious path planning.
Tensor Atomic Cluster Expansion (TACE): equivariant atomistic machine learning in Cartesian space unifying scalar and tensorial modeling for chemistry applications.
Taxonomy-aware dynamic motion generation for robots using hyperbolic manifolds to incorporate hierarchical biomechanical structure into movement models.
Self-speculative masked diffusions: discrete data generative models reducing function evaluations through speculative sampling without factorization approximations.
TCR-EML: explainable machine learning model layers for predicting T cell receptor-peptide MHC binding with interpretability for immunotherapy applications.
Meta-evaluation study analyzing reliability of micro-benchmarks for ranking LLMs, comparing against full benchmarks and random sampling approaches.
CanvasMAR: masked autoregressive video generation model improved with canvas mechanism to reduce frame distortion and enhance sampling quality with few steps.
Study on model collapse in generative models trained iteratively on synthetic data, proposing verification methods to prevent performance degradation and reverse collapse trends.
Interval-based reachability analysis method for Neural ODEs using mixed monotonicity techniques to verify continuous-time machine learning models of dynamical systems.
Real-time learning framework for predicting dynamic obstacle motions in robotic systems using Hankel-DMD for online nonlinear model identification from noisy measurements.
FireScope-Bench: dataset and benchmark for wildfire risk prediction using satellite imagery, climate data, and chain-of-thought reasoning with multimodal integration.
Test-time reinforcement learning method for LLMs using token-selective entropy-band regularization to prevent response collapse.
Proposes DFIR-DETR transformer architecture for small object detection addressing backbone attention and feature aggregation issues.
Analyzes robustness of subset selection-based visual explanation methods under distribution shifts and out-of-distribution conditions.
Applies topological data analysis to CT imaging for improved feature extraction in medical imaging ML models.
Improves audio-visual speech recognition in noisy environments using mask-free purification before feature fusion.
Proposes optical neural network implementation using linear optical resources and phase-shift encoding for practical photonic machine learning.
Demonstrates online unsupervised Hebbian learning in photonic neuromorphic networks for energy-efficient neural computation.
Addresses exploration collapse in large reasoning models post-training by proposing latent exploration decoding to restore sampling diversity.
Validates interpretability of saliency maps in siRNA efficacy prediction using perturbation-based counterfactual sensitivity testing.
Container-free reinforcement learning framework for training software engineering agents at scale without per-task container overhead.
Open-source system for multimodal data acquisition in robot-assisted minimally invasive surgery without relying on proprietary robot telemetry.
Proposes carbon-efficient neural ranking architecture for information retrieval using semantic-guided diffusion tuning.