2/27/2026
Benchmarking IoT Time-Series AD with Event-Level Augmentations
Benchmarking framework for IoT time-series anomaly detection using event-level augmentations simulating real-world perturbations.
2/27/2026
Soft Sequence Policy Optimization
Introduces Soft Sequence Policy Optimization, advancing LLM alignment methods beyond GRPO with sequence-level importance sampling.
2/27/2026
On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference
Theoretical analysis connecting random network distillation, deep ensembles, and Bayesian inference for uncertainty quantification in deep learning.
2/27/2026
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
Shows Pass@k optimization can degrade Pass@1 due to prompt interference, revealing trade-offs in LLM fine-tuning for code generation.
2/27/2026
AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression
AngelSlim comprehensive toolkit for large model compression combining quantization, pruning, distillation, and speculative decoding.
2/27/2026
Muon+: Towards Better Muon via One Additional Normalization Step
Muon+ optimizer improves LLM pre-training by adding normalization step after gradient orthogonalization.
2/27/2026
Hardness of Maximum Likelihood Learning of DPPs
Analyzes hardness of maximum likelihood learning for Determinantal Point Processes used in subset selection.
2/27/2026
Approximation Error and Complexity Bounds for ReLU Networks on Low-Regular Function Spaces
Theoretical bounds on approximation error for ReLU networks approximating low-regularity bounded functions.
2/27/2026
Differential Privacy of Quantum and Quantum-Inspired Classical Recommendation Algorithms
Studies differential privacy of quantum and quantum-inspired classical recommendation algorithms.
2/27/2026
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
Unbiased Sliced Wasserstein kernel addresses exposure bias in audio captioning systems to improve caption quality.
2/27/2026
SODAs: Sparse Optimization for the Discovery of Differential and Algebraic Equations
SODAs algorithm for data-driven discovery of differential and algebraic equations from sparse optimization approach.
2/27/2026
Composable and adaptive design of machine learning interatomic potentials guided by Fisher-information analysis
Adaptive physics-inspired design for machine-learning interatomic potentials using Fisher information matrix guidance.
2/27/2026
Knowledge Fusion of Large Language Models Via Modular SkillPacks
Knowledge Fusion via SkillPacks enables efficient cross-capability transfer between LLMs for multi-task integration and model compression.
2/27/2026
LinGuinE: Longitudinal Guidance Estimation for Volumetric Tumour Segmentation
LinGuinE PyTorch framework for longitudinal volumetric tumor segmentation combining image registration and guided segmentation.
2/27/2026
On the Interpolation Error of Nonlinear Attention versus Linear Regression
Theoretical analysis of nonlinear attention mechanisms compared to linear regression for understanding interpolation error.
2/27/2026
Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?
Studies exchangeability versus i.i.d assumptions for handling distribution shifts when pooling medical imaging datasets.
2/27/2026
LayerT2V: A Unified Multi-Layer Video Generation Framework
LayerT2V framework for text-to-video generation producing editable layered representations for professional workflows.
2/27/2026
Understanding protein function with a multimodal retrieval-augmented foundation model
PoET-2 multimodal retrieval-augmented foundation model for understanding protein function using protein language models.
2/27/2026
Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
Adaptive hybrid caching optimization for efficient inference in video diffusion transformer models to reduce computational cost.
2/27/2026
Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later
Geometric autoencoders for Bayesian inference to recover physical system information from limited noisy observations.
2/27/2026
Inducing Dyslexia in Vision Language Models
Studies dyslexia-like behavior in vision-language models by reducing visual word form area activity to test reading impairment mechanisms.
2/27/2026
Generative Value Conflicts Reveal LLM Priorities
ConflictScope pipeline automatically evaluates how LLMs prioritize different values when facing conflicting objectives.
2/27/2026
Secure and reversible face anonymization with diffusion models
Face anonymization using diffusion models to protect identity while preserving image quality and enabling authorized recovery.
2/27/2026
Atlas-free Brain Network Transformer
Atlas-free Transformer approach for brain network analysis without standardized anatomical templates.
2/27/2026
DeepMartingale: Duality of the Optimal Stopping Problem with Expressivity and High-Dimensional Hedging
Deep learning framework for optimal stopping problems using martingale representation for high-dimensional financial hedging.
2/27/2026
Throwing Vines at the Wall: Structure Learning via Random Search
Random search algorithms for vine copula structure learning in multivariate dependence modeling.
2/27/2026
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Supervised Reinforcement Learning method for training small open-source LLMs on multi-step reasoning tasks, combining SFT and RLVR approaches.
2/27/2026
Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models
Method for efficient LLM inference via speculative decoding with dynamic tree construction accounting for system variables.
2/27/2026
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Temporal Sparse Autoencoders using sequential language structure for discovering interpretable features in LLM representations.
2/27/2026
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Analysis of energy efficiency of small LLMs on local hardware accelerators versus cloud inference for practical deployment.
2/27/2026
VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
VLM-Pruner: Token pruning method for vision-language models addressing spatial sparsity and inter-token redundancy.
2/27/2026
One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
One-step diffusion samplers using self-distillation and deterministic flow for efficient sampling from unnormalized distributions.
2/27/2026
Imitation Game: Reproducing Deep Learning Bugs Leveraging an Intelligent Agent
Intelligent agent system for automatically reproducing deep learning bugs by leveraging nondeterminism and environment coupling.
2/27/2026
LeanCat: A Benchmark Suite for Formal Category Theory in Lean (Part I: 1-Categories)
LeanCat: Benchmark of 100 formalized category theory tasks in Lean evaluating LLMs on library-grounded abstraction and theorem proving.
2/27/2026
Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging
Physics-based noise synthesis framework for astronomical imaging denoising using learning-based methods.
2/27/2026
Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives
Framework connecting GFlowNets to Markov chain reversibility to control exploration-exploitation trade-off during training.
2/27/2026
VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
Method for disentangling style and content in human motion using residual quantized representations for motion style transfer.
2/27/2026
The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training
Study of multi-query synthesis for dense retriever training showing quality-diversity trade-off benefits out-of-domain and multi-hop retrieval.
2/27/2026
GPT-4o Lacks Core Features of Theory of Mind
Evaluation showing GPT-4o lacks causal models of mental states required for true Theory of Mind despite benchmark performance.
2/27/2026
Large-scale online deanonymization with LLMs
Agent with internet access performs at-scale deanonymization of Hacker News and interview participants using LLMs.
2/27/2026
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
LLM4Cov: Offline agent-learning framework using execution feedback from hardware simulators for test generation with high coverage.
2/27/2026
Scaling Laws for Precision in High-Dimensional Linear Regression
Theoretical analysis of how low-precision quantization affects model and data capacities in high-dimensional linear regression.
2/27/2026
DRESS: A Continuous Framework for Structural Graph Refinement
Framework for improving graph neural network efficiency using continuous differential equations to avoid prohibitive tensor operations.
2/27/2026
Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
Method to decompose epistemic uncertainty in Bayesian deep learning by per-class contributions for asymmetric cost classification tasks.
2/27/2026
Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models
Research on LLM capacity to be persuaded and detect manipulation, testing vigilance and persuasion in high-stakes decision-making contexts.
2/27/2026
Multilingual Safety Alignment Via Sparse Weight Editing
Research paper on sparse weight editing for multilingual LLM safety alignment across low-resource languages without expensive retraining.
2/27/2026
Add pre-flight credit check before PR creation on coverage dashboard
UX improvement for coverage dashboard: added pre-flight credit check before PR creation to prevent wasted requests.
2/27/2026
Show HN: Agentplace, the tool we built to become a 20x company
Agentplace tool for building and automating AI agents at scale. Addresses challenges in agent development and scaffolding.
2/27/2026
Microsoft's Copilot Tasks AI uses its own computer to get things done
Microsoft Copilot Tasks uses AI agent to autonomously complete user tasks like converting emails to slideshows.
2/27/2026
Show HN: Ambit Shell – Easy Remote Shell for OpenClaw, Claude Code, etc.
Remote shell tool for Claude Code and similar applications. Content primarily documentation references.