Analysis of safety drift in tool-augmented LLM agents, showing ranking metrics miss unsafe recommendations in high-stakes financial advisor scenarios.
Surgical duration prediction using retrieval-augmented LLMs and Bayesian averaging without fine-tuning, applied to hospital resource management.
Study on improving LLM code generation with private libraries, showing retrieval-based API documentation injection is insufficient for effective library usage.
Spectral Edge Dynamics quantifies transformer training trajectory structure through rolling SVD, identifying boundary between optimization directions and noise.
LICA dataset of 1.55M layered graphic design compositions with hierarchical metadata for layout understanding and generation.
Analysis of multimodal LLM-generated natural language explanations for face verification on unconstrained images using IJB-S dataset.
Survey of deployment constraints and mitigation strategies for foundation models in resource-constrained embodied edge systems.
HopChain improves vision-language reasoning through multi-hop data synthesis to address perception, reasoning, and hallucination errors in VLMs.
SCALE addresses bottlenecks in virtual cell perturbation prediction using foundation models for in silico experimentation.
Multimodal multilingual benchmark with 3000 texts and 6000 images for detecting harmful humor across English and Arabic.
TDAD is open-source tool performing impact analysis for AI coding agents to detect and prevent regressions in test-driven agentic development.
Geometric analysis of Rotary Positional Embedding performance breakdown on long inputs, explaining channel rotation distribution shift.
Architectural approach using per-layer supervision to expose hidden modularity in Transformers, enabling interpretability and causal control of components.
Methods for distinguishing system failures from domain shifts in industrial data streams using anomaly detection techniques.
Graph-regularized Koopman mean-field game framework for controlling high-dimensional neural dynamics during epileptic seizures.
Systematic methodology for fine-tuning domain-specific Japanese small language models, identifying optimal training scale (4k samples), base models, and quantization strategies.
Mathematical framework for comparing multi-agent swarm configurations using quotient geometry and persistence-stable metrics.
Zero-knowledge proof system enabling cryptographic verification that proprietary LLM API outputs come from claimed models, preventing model substitution or degradation.
Investigates how mechanistic interpretability features survive extreme neural network sparsification using adaptive sparsity scheduling in VAE-SAE architectures.
Lightweight adaptation method for LLM-based technical service agents using latent logic augmentation and noise reduction without full retraining.
Variational Phasor Circuit architecture for brain-computer interface classification using phase-native learnable parameters inspired by quantum circuits.
Step-level experience augmented reinforcement learning for multi-turn LLM agents that dynamically retrieve and refine experiences throughout episodes.
Meta-BayFL framework for federated learning with probabilistic approaches to handle data uncertainty and heterogeneity while managing computational overhead.
Proposes dynamic constraints for reinforcement learning fine-tuning that adapt to model capabilities, resolving tension between optimization and constraint satisfaction.
Neuro-symbolic framework combining neural operators with economic constraints for interpretable quantitative finance models respecting no-arbitrage principles.
Tula optimizes distributed large-batch training by balancing communication overhead, computation cost, and model generalization across scaling configurations.
Proposes VC-Soup method for aligning LLMs with multiple potentially conflicting human values through value-consistency guided optimization.
LLM-augmented computational phenotyping framework for discovering clinical subphenotypes in Long COVID through iterative hypothesis generation and evidence extraction.
Framework for detecting conflicts in policy languages that use probabilistic ML predicates, applied to semantic router DSL for LLM routing systems.
Improves PDE surrogate model training through gradient-informed temporal sampling strategies that optimize rollout accuracy under fixed data budgets.
Proposes AGRI-Fidelity framework to evaluate reliability of explainable AI for poultry disease detection in noisy farm environments.
Framework for evaluating reasoning-based LLMs on de novo molecular generation and drug discovery without requiring ground-truth molecule pairs.
Proposes Interventional Boundary Discovery to identify causal state dimensions agents can control, using Pearl's do-operator for causal identification.
Addresses the squeezing effect in Direct Preference Optimization (DPO) for LLM alignment using sharpness-aware minimization in logit space.
Studies alignment evaluation in LLMs by examining political censorship in Chinese language models, focusing on routing mechanisms beyond concept detection and refusal behaviors.
Additive Gaussian processes for wind farm power prediction using population-based structural health monitoring perspective.
Path-constrained mixture-of-experts architecture constraining expert routing paths to improve statistical efficiency and meaningful parameter structure.
ALIGN: adversarial learning framework for session-invariant speech neuroprosthesis decoding from brain-computer interfaces.
Neural graph representation learning with RL for approximate subgraph matching, an NP-hard problem in graph analysis.
Autocurriculum training methods with provable benefits for chain-of-thought reasoning in language models with reduced data/compute costs.
Vector-field reward shaping for offline RL to enable safe exploration near dataset boundaries using simulator confidence.
Epistemic GANs using Dempster-Shafer theory to improve output diversity and architectural enhancements for generative models.
Comprehensive book on mathematical foundations of deep learning covering neural network approximation theory, optimal control, RL, and generative models.
RE-SAC: ensemble deep reinforcement learning for bus fleet control that disentangles aleatoric and epistemic uncertainty.
Flow matching approach for de novo molecular structure elucidation from mass spectra using deep generative models.
AFBS-BO framework for automated hyperparameter optimization of sparse attention mechanisms in transformers via adaptive fidelity Bayesian optimization.
Quantum multi-armed and stochastic linear bandits algorithms robust to noise in NISQ devices, achieving quadratic speedups over classical methods.
Sample-efficient reward estimation method for RL with verifiable rewards in large language model post-training.
Training suite for film shot language understanding using vision-language models to match expert cinematographic analysis.
Distributed asynchronous RL framework for Vision-Language-Action models with integrated trainable world models.