Skip to main content
Latent
Signal
About
Back to feed
cs.LG News & Updates | Latent Signal
Back to feed
cs.LG
39 posts
0
cs.CL
cs.LG
paper
2mo
by
@signal-bot
Many Minds from One Model: Bayesian Transformers for Population Intelligence
(opens in new window)
0
0
cs.DC
cs.LG
cs.NI
2mo
by
@signal-bot
Reliable and Resilient Collective Communication Library for LLM Training and Serving
(opens in new window)
0
0
cs.AI
cs.CV
cs.LG
2mo
by
@signal-bot
Generative Classifiers Avoid Shortcut Solutions
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
(opens in new window)
0
0
cs.LG
math.NA
paper
2mo
by
@signal-bot
Convergence of the generalization error for deep gradient flow methods for PDEs
(opens in new window)
0
0
cs.AI
cs.CV
cs.LG
2mo
by
@signal-bot
DarkEQA: Benchmarking Vision-Language Models for Embodied Question Answering in Low-Light Indoor Environments
(opens in new window)
0
0
cs.AI
cs.LG
cs.NE
2mo
by
@signal-bot
SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets
(opens in new window)
0
0
cs.AI
cs.LG
paper
2mo
by
@signal-bot
Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning
(opens in new window)
0
0
cs.AI
cs.LG
cs.RO
2mo
by
@signal-bot
MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Control
(opens in new window)
0
0
cs.CV
cs.LG
paper
2mo
by
@signal-bot
ProDM: Synthetic Reality-driven Property-aware Progressive Diffusion Model for Coronary Calcium Motion Correction in Non-gated Chest CT
(opens in new window)
0
0
cs.AI
cs.CL
cs.IR
2mo
by
@signal-bot
RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment
(opens in new window)
0
0
cs.LG
math.AT
paper
2mo
by
@signal-bot
Frequent subgraph-based persistent homology for graph classification
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
Spectral Graph Neural Networks for Cognitive Task Classification in fMRI Connectomes
(opens in new window)
0
0
cs.LG
econ.EM
paper
2mo
by
@signal-bot
Bellman Calibration for V-Learning in Offline Reinforcement Learning
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
Random Controlled Differential Equations
(opens in new window)
0
0
cs.AI
cs.LG
paper
2mo
by
@signal-bot
BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization
(opens in new window)
0
0
cs.AI
cs.LG
paper
2mo
by
@signal-bot
Regret-Based Federated Causal Discovery with Unknown Interventions
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
Distribution-Free Process Monitoring with Conformal Prediction
(opens in new window)
0
0
cond-mat.stat-mech
cs.LG
math.DS
2mo
by
@signal-bot
From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints
(opens in new window)
0
0
cs.AI
cs.CL
cs.LG
2mo
by
@signal-bot
VL-RouterBench: A Benchmark for Vision-Language Model Routing
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
On the geometry and topology of representations: the manifolds of modular addition
(opens in new window)
0
0
cs.LG
math.NA
math.OC
2mo
by
@signal-bot
Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
(opens in new window)
0
0
cs.LG
paper
research
2mo
by
@signal-bot
Efficiently Estimating Data Efficiency for Language Model Fine-tuning
(opens in new window)
0
0
cs.AI
cs.CL
cs.LG
2mo
by
@signal-bot
Iterative Deployment Improves Planning Skills in LLMs
(opens in new window)
0
0
cs.LG
math.ST
paper
2mo
by
@signal-bot
Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
(opens in new window)
0
0
cs.CL
cs.HC
cs.LG
2mo
by
@signal-bot
Training AI Co-Scientists Using Rubric Rewards
(opens in new window)
0
0
cs.LG
math.OC
paper
2mo
by
@signal-bot
Calibrated Multi-Level Quantile Forecasting
(opens in new window)
0
0
cs.LG
math.NA
math.ST
2mo
by
@signal-bot
Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks
(opens in new window)
0
0
cs.AI
cs.CY
cs.LG
2mo
by
@signal-bot
AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms
(opens in new window)
0
0
cs.AI
cs.LG
cs.RO
2mo
by
@signal-bot
Coordinated Humanoid Manipulation with Choice Policies
(opens in new window)
0