archive
Every paper Pith has read. Search by title, abstract, or pith.
14903 papers in cs.LG · page 8
-
Quantum amplitudes adapt to predict network link changes
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
-
Learning-based CCs degrade less than traditional ones under attack
CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
-
Topological index spots wireless receiver shifts early
Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology
-
Optimal control yields tunable noise schedules for diffusion models
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
-
Physics laws inside neural nets speed up power-grid modeling
Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review
-
7B model beats larger ones at Lean proof optimization
ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
-
Predicting switch timing improves game strategy advice
When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
-
Flow model in tree space cuts divergence to phylogenetic posteriors
PhylaFlow: Hybrid Flow Matching in Billera-Holmes-Vogtmann Tree Space for Phylogenetic Inference
-
Truncating CoT exposes evasive contamination in LLMs
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
-
Accumulating oracle signals yields token-level advantages for LLMs
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
-
Accumulating oracle signals yields token-level advantages in one pass
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
-
Dictionary realignment keeps OOD explanations faithful
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
-
Equal-variance structural VARs identified only up to orthogonal transforms and scale
Causal Discovery in Structural VAR Models Under Equal Noise Variance
-
Tensor Cache stores evicted tokens in outer-product memory
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
-
Energy gating lifts transformer loss by 0.1 with tiny overhead
Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention
-
On-policy training halves LLM sycophancy without capability loss
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
-
Expert comparisons guide nanoscale experiments without scalar goals
Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale
-
Symbolic search recovers exact discrete distribution formulas
Symbolic Density Estimation for Discrete Distributions
-
Truncation makes neural likelihood work for long state sequences
Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models
-
Embeddings support 99% accurate tomato field mapping
Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis
-
Optimizers create different spectral scaling laws in the same model
Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws
-
Geometry-aware calibration closes entropy gaps for LLM optimization
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
-
One platform unifies the full world model research pipeline
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
-
Agentic AI uses 4.33x more energy per successful goal than linear baselines
Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
-
KL divergence to GPs splits into three costs for neural processes
Three Costs of Amortizing Gaussian Process Inference with Neural Processes
-
DivSkill-SQL lifts Text-to-SQL accuracy by up to 11 points
Residual Skill Optimization for Text-to-SQL Ensembles
-
MMD-balls as credal sets bound worst-case risk in test-time adaptation
MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
-
Privacy profiles connect randomized smoothing to differential privacy for joint…
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
-
LLMs lose accuracy on complex noisy logs for intrusion detection
HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection
-
Manifold projections steer LLMs clear of reasoning mistakes
Manifold-Guided Attention Steering
-
Local rerollouts fix unfair credit assignment in memory LLM agents
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
-
Sampling-based inference reaches parity with optimization in BNNs
Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning
-
Only full-domain utilities make OCE risk measures PAC-learnable in RL
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
-
ML on calcium scans predicts obstructive CAD
Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans
-
External data files fix binding failures in text-to-optimization
Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization
-
Pairwise comparisons yield unbiased preference percentiles
PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation
-
Calcium-omics features lift ischemia prediction from CT scans to 99% precision
Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring
-
Thresholding fixes class imbalance in PFNs for tabular data
Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification
-
Support-aware method certifies ad reserve policies from logs
Support-aware offline policy selection for advertising marketplaces
-
Audit tool uncovers hidden differences in accurate AI drug models
I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models
-
Lightweight cross-encoder matches LLM judges for caption evaluation
BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model
-
Exact doubly stochastic mixes via transportation polytopes
TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes
-
Adaptive bias lets neural samplers cross discrete energy barriers
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
-
Market maker adapts to new regimes without retraining
Zero-shot adaptation to order book dynamics
-
Projection matrix aligns tokenizers for better distillation
X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
-
Representation Gap is governed by task intrinsic dimension
Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective
-
Stochastic policy amortizes diffusion guidance for 5x faster sampling
Hierarchical Variational Policies for Reward-Guided Diffusion
-
Actor updates match value gradients under differentiable rollouts
Value-Gradient Hypothesis of RL for LLMs
-
Fine-tuned detectors amplify a pretrained typicality axis
Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
-
Entmax turns KV cache truncation into exact support recovery
EntmaxKV: Support-Aware Decoding for Entmax Attention
4 Piths