Show HN: Restailor – open-source AI job fit/resume tailor/job tracker
Open-source resume and job application tool using LLM integrations from multiple providers for tailoring and job tracking.
Open-source resume and job application tool using LLM integrations from multiple providers for tailoring and job tracking.
Comparison of three methods (Ablation, Heretic, Obliteratus) for removing refusal behaviors from LLMs.
Title only, no content provided.
Task-aware representation learning framework for upscaling sparse terrestrial carbon flux measurements globally.
Societies of large language models collaborating through natural language interfaces to solve problems, inspired by Minsky's society of mind concept.
Continuous-time optimal stopping problem formulated as reinforcement learning with randomized stopping times and exploration regularization.
Benchmark dataset for evaluating neural point processes on earthquake forecasting, comparing against classical ETAS models.
Research on how diffusion models memorize training data, measuring latent dimensionality collapse on low-dimensional manifolds as data becomes scarce.
Statistical framework for pairwise comparison modeling that relaxes stochastic transitivity assumptions used in Bradley-Terry and Thurstone models.
Study examining adversarial robustness of deep speech denoising models, showing four DNS models vulnerable to psychoacoustically hidden adversarial noise attacks.
Image fusion method using granular ball priors for few-shot learning without direct supervision signals.
Offline reinforcement learning approach for joint pricing and inventory optimization with censored demand data.
Diffusion-based feedback control framework for managing probability density in nonlinear dynamical systems.
Spiking neural networks with adaptive task-switching for resource-constrained multi-task reinforcement learning in autonomous agents.
Data-driven survey identifying 14,648 papers on LLM limitations from 2022-2025 using LLM-based classification.
System using multiple pre-trained models and consistency-based reasoning to handle distributional shifts in novel environments.
Interleaved online fine-tuning method enabling LLMs to acquire capabilities beyond base model through reinforcement learning.
Survey of differential privacy techniques from symbolic AI through LLMs, covering definitions and applications.
Yokai: benchmark environment for zero-shot coordination in cooperative AI with belief tracking over space and time.
Tensor completion algorithm using low-rank assumptions for recovering multi-way data tensors from partial observations.
Neural function encoder method for solving parametric optimal control problems with zero-shot transfer across objectives.
Theoretical PAC-Bayes bounds for Markov chains with empirical constants that don't require unknown data properties.
Empirical study analyzing intra-modality and inter-modality dependencies in multi-modal learning benchmark datasets.
RADAR: dynamic routing system that selects optimal reasoning LLM models based on task difficulty and cost-performance tradeoffs.
Neuroscience study using diffusion models and mutual information to analyze visual cortex neural populations.
Self-supervised learning evaluation for sleep staging with wearable EEG devices.
KVTC: transform coder that compresses KV caches for efficient LLM inference storage and memory management.
GNN with multi-task learning for resource allocation in hybrid IoT networks combining optical and RF communication.
CostNav benchmark evaluating physical AI agents on real-world economic metrics for autonomous delivery systems beyond task success.
Co-design framework jointly optimizing robot hand morphology and dexterous control policies across multiple embodiments.
Neural network decoder (AlphaQubit 2) for quantum error correction enabling fast and scalable decoding of topological quantum codes.
Closed-loop drug discovery system using language models, property alignment, and strategic search for de novo ligand design.
Proprioceptive-Privileged contrastive learning framework for sample-efficient whole-body control in humanoid robots using reinforcement learning.
Low-illumination enhancement for anime scenery images using uncertainty framework and unpaired dataset.
First-order analysis of how cross-entropy training reshapes transformer attention geometry for probabilistic reasoning.
Error analysis of Bayesian inverse problems using generative models as priors with quantitative bounds.
Singular Bayesian neural networks using low-rank factorization to reduce parameters from O(mn) while maintaining uncertainty calibration.
Theoretical characterization of generative distortion phenomenon where classifier-free guidance causes loss of diversity in diffusion model outputs.
Theoretical analysis of asymmetric rank-one spiked tensor models in high-dimensional regime with non-Gaussian noise.
GOT-JEPA: Object tracking system using joint-embedding predictive architecture with model adaptation and occlusion handling.
ZACH-ViT: Compact vision transformer removing positional embeddings for medical imaging where spatial layout is weakly informative.
Conformal prediction analysis examining operational tradeoffs beyond coverage for deployed ML systems.
Benchmarking study comparing graph neural networks against classical heuristics on hard constraint satisfaction problems.
Autonomous AI analysts built on LLMs analyzing same dataset independently, quantifying variability in research conclusions without human coordination.
Study of how LLMs develop early syntactic structures that persist as errors through training, using OPT model on BabyLM dataset.
CARE: Evidence-grounded agentic framework using visual language models for medical reasoning with explainability and clinical accountability.
CFG-Ctrl: Control-based framework reinterpreting classifier-free guidance as control signal for diffusion models.
RACAS: Framework for controlling diverse robotic platforms with a single agentic system through unified interface.
Multi-agent game theory study analyzing coordination dynamics in Battle of the Exes variant using temporal metrics.
Systematic comparison of training objectives (cross-entropy, prototype, triplet, AP loss) for out-of-distribution detection in image classification models.