Newsletter
Users
Feeds
Add Feed
L
@leniqa1520
0
Feed (87)
Sources (1)
Categories
Type
Loading articles...
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
October 6th, 2026
•
by
machinelearning.apple.com
Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems
October 5th, 2026
•
by
machinelearning.apple.com
Limits of Confidence in Diffusion
October 2nd, 2026
•
by
machinelearning.apple.com
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
October 2nd, 2026
•
by
machinelearning.apple.com
RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback
October 1st, 2026
•
by
machinelearning.apple.com
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
October 1st, 2026
•
by
machinelearning.apple.com
SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation
September 30th, 2026
•
by
machinelearning.apple.com
On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study
September 30th, 2026
•
by
machinelearning.apple.com
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
September 29th, 2026
•
by
machinelearning.apple.com
Faster Rates for Federated Variational Inequalities
September 28th, 2026
•
by
machinelearning.apple.com
A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
September 24th, 2026
•
by
machinelearning.apple.com
Compressing Streaming Neural Audio Encoders via Latent-Space Distillation
September 24th, 2026
•
by
machinelearning.apple.com
How to Guide Your Language Flow
September 23rd, 2026
•
by
machinelearning.apple.com
Dynamically Scaled Activation Steering
September 18th, 2026
•
by
machinelearning.apple.com
REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff
September 17th, 2026
•
by
machinelearning.apple.com
How Value Induction Reshapes LLM Behaviour
September 16th, 2026
•
by
machinelearning.apple.com
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
September 16th, 2026
•
by
machinelearning.apple.com
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
September 16th, 2026
•
by
machinelearning.apple.com
Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs
September 16th, 2026
•
by
machinelearning.apple.com
Shared Selective Persistent Memory for Agentic LLM Systems
September 16th, 2026
•
by
machinelearning.apple.com
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
September 11th, 2026
•
by
machinelearning.apple.com
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
September 11th, 2026
•
by
machinelearning.apple.com
DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
September 11th, 2026
•
by
machinelearning.apple.com
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
September 2nd, 2026
•
by
machinelearning.apple.com
Agent Seer: Synthesizing Scenarios from Specification Understanding
August 28th, 2026
•
by
machinelearning.apple.com
LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic Beliefs
August 28th, 2026
•
by
machinelearning.apple.com
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
August 27th, 2026
•
by
machinelearning.apple.com
Luce: Relightable Gaussians for 3D Asset Generation
August 26th, 2026
•
by
machinelearning.apple.com
IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
August 26th, 2026
•
by
machinelearning.apple.com
PROOF-Gen: From Optimized Data to Better Distillation
August 26th, 2026
•
by
machinelearning.apple.com