ClaudeChatGPTGitHubGemini

gl-apple-ml

Latest items from gl-apple-ml on ClawDigest — updated automatically as new stories are ingested.

ProText: A Benchmark Dataset for Measuring (Mis)gendering in Long-Form Texts

3mo ago

Metric-Dependent Annotation Saturation for Learning from Label Distributions

11d 2h ago

Beyond Real Data: Synthetic Data through the Lens of Regularization

3mo ago

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

1mo ago

Bootstrapping Sign Language Annotations with Sign Language Models

2mo ago

Apple Workshop on Privacy-Preserving Machine Learning & AI 2026

1mo ago

Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents

2mo ago

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

2mo ago

ParaRNN: Large-Scale Nonlinear RNNs, Trainable in Parallel

2mo ago

Multi-Agent Teams Hold Experts Back

1d 23h ago

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

1d 23h ago

Amortizing Maximum Inner Product Search with Learned Support Functions

1d 23h ago

On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

1d 23h ago

Learning Structured Reasoning via Tractable Trajectory Control

1d 23h ago

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

1mo ago

Adaptive Thinking: Large Language Models Know When to Think in Latent Space

2mo ago

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss

2mo ago

A Theoretical Framework for Acoustic Neighbor Embeddings

2mo ago

Entropy-Preserving Reinforcement Learning

3mo ago

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

1mo ago

RVPO: Risk-Sensitive Alignment via Variance Regularization

1mo ago

What Matters in Practical Learned Image Compression

1mo ago

Apple Machine Learning Research at ICLR 2026

2mo ago

International Conference on Learning Representations (ICLR) 2026

2mo ago

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

1mo ago

Learning Long-Term Motion Embeddings for Efficient Kinematics Generation

2mo ago

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment

3mo ago

Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels

10d 21h ago

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts

2mo ago

Velox: Learning Representations of 4D Geometry and Appearance

1mo ago

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing

1mo ago

ACM Human-Computer Interaction Conference (CHI) 2026

2mo ago

Introducing the Third Generation of Apple’s Foundation Models

25d 19h ago

Learning Unmasking Policies for Diffusion Language Models

1d 19h ago

Residual Context Diffusion Language Models

1d 19h ago

Conformal Thinking: Risk Control for Reasoning on a Compute Budget

1d 19h ago

Anti-Causal Domain Generalization: Leveraging Unlabeled Data

1d 19h ago

Can Large Language Models Understand Context?

2mo ago

What Do Your Logits Know? (The Answer May Surprise You!)

2mo ago

International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2026

2mo ago

From Where Things Are to What They’re For: Benchmarking Spatial–Functional Intelligence for Multimodal LLMs

1mo ago

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning

1mo ago

Normalizing Flows with Iterative Denoising

1mo ago

Local Mechanisms of Compositional Generalization in Conditional Diffusion

2mo ago

SpecMD: A Comprehensive Study on Speculative Expert Prefetching

1mo ago

SQUIRE: Interactive UI Authoring via Slot QUery Intermediate REpresentations

2mo ago

DSO: Direct Steering Optimization for Bias Mitigation

2mo ago

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

2mo ago

EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments

1mo ago

Efficient Privacy Loss Accounting for Subsampling and Random Allocation

2mo ago

← back to ClawDigest