Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
3+ day, 19+ hour ago (119+ words) Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference December 11, 2025research area Methods and Algorithms, research area Speech and Natural Language Processing November 19, 2024research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLP, Workshop at NeurIPS This paper…...
Scaling Categorical Flow Maps
4+ day, 1+ hour ago (315+ words) Apple Machine Learning Research Scaling Categorical Flow Maps Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including accelerated sampling…...
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling - Apple Machine Learning Research
3+ week, 19+ hour ago (439+ words) Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling Apple Machine Learning Research Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling AuthorsZhen Zhang†, Changyi Yang‡§, Zijie Xia§, Zhen Yang, Chengzhi Liu†, Zhaotiao Weng†, Yepeng Liu†, Haobo Chen…...
When Unlearning Is Free: Leveraging Low Influence Points to Reduce Computational Costs
3+ week, 4+ day ago (253+ words) Apple Machine Learning Research When Unlearning Is Free: Leveraging Low Influence Points to Reduce Computational Costs As concerns around data privacy in machine learning grow, the ability to unlearn—or remove—specific data points from trained models becomes increasingly important....
Personalizing Incremental Video Search with Hybrid Text and ID Embeddings - Apple Machine Learning Research
3+ week, 4+ day ago (64+ words) BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale December 11, 2024research area Knowledge Bases and Search, research area Methods and Algorithmsconference AAAI August 16, 2023research area Knowledge Bases and Search, research area Methods and Algorithms Our…...
Interactive Proofs for General Distribution Properties
3+ week, 4+ day ago (375+ words) Apple Machine Learning Research Interactive Proofs for General Distribution Properties Suppose Alice has collected a small number of samples from an unknown distribution, and would like to learn about the distribution. Bob, an untrusted data analyst, claims to have run…...
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
1+ mon, 19+ hour ago (105+ words) This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (ARES) 2026. June 29, 2022research area General Earlier this year, Apple hosted the Privacy-Preserving Machine Learning (PPML)…...
Weblica: Scalable and Reproducible Training Environments for Visual Web Agents
1+ mon, 4+ day ago (135+ words) AuthorsOğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong, Anders Boesen Lindbo Larsen, Afshin Dehghan August 6, 2024research area Methods and Algorithms, research area Speech and Natural Language Processingconference ACL Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling This paper has…...
TopoPrimer: The Missing Topological Context in Forecasting Models
1+ mon, 5+ day ago (62+ words) AuthorsZara Zetlin, Kayhan Moharreri, Maria Safi BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale December 11, 2024research area Knowledge Bases and Search, research area Methods and Algorithmsconference AAAI Learning Insulin-Glucose Dynamics in the Wild…...
Understanding Annotator Safety Policy with Interpretability
1+ mon, 5+ day ago (102+ words) View source code (GitHub) March 24, 2026research area Computer Vision, research area Speech and Natural Language ProcessingWorkshop at ICLR This paper was accepted at the Principled Design for Trustworthy AI — Interpretability, Robustness, and Safety across Modalities Workshop at ICLR 2026. What exactly makes…...