https://machinelearning.apple.com Apple machine learning teams are engaged in state of the art research in machine learning and artificial intelligence. Learn about the latest advancements. en Wed, 30 Sep 2026 00:00:00 GMT effectiveness-fluency-llm-conditioning https://machinelearning.apple.com/research/effectiveness-fluency-llm-conditioning Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. Current approaches to conditioning are often evaluated with a narrow focus on their effectiveness at injecting or removing a target concept, neglecting generation quality. We systematically investigate a range of conditioning methods in both injection and removal scenarios. We find that efficient steering methods frequently achieve conditioning at a steep cost to fluency. Furthermore, we identify a critical yet… Wed, 30 Sep 2026 00:00:00 GMT sclate-agent-training-evaluation https://machinelearning.apple.com/research/sclate-agent-training-evaluation Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. Yet existing benchmarks and training frameworks schedule only the benchmark’s own events, leaving each benchmark and agent pair to build a custom scheduling loop. We present SCLATE, an execution substrate where benchmarks and unmodified agents each add their events to one open event scheduler through an adapter. A hybrid simulated clock… Wed, 30 Sep 2026 00:00:00 GMT communication-bottleneck-serialization https://machinelearning.apple.com/research/communication-bottleneck-serialization When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survives this bottleneck? We propose a round-trip protocol that answers this question empirically for tree-structured expressions. A generator converts a procedurally generated arithmetic expression into a word problem, a separate extractor recovers the expression from the word problem alone, and symbolic equivalence provides an exact oracle. Evaluating all pairwise combinations of sixteen models yields… Tue, 29 Sep 2026 00:00:00 GMT federated-variational-inequalities https://machinelearning.apple.com/research/federated-variational-inequalities In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substantial progress, a significant gap remains between existing convergence rates and the state-of-the-art bounds known for federated convex optimization. In this work, we address this limitation by establishing a series of improved convergence rates. First, we show that, for general smooth and monotone variational inequalities, the classical Local Extra SGD algorithm admits tighter guarantees under a refined analysis… Mon, 28 Sep 2026 00:00:00 GMT latent-space-distillation https://machinelearning.apple.com/research/latent-space-distillation System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the language model reads. Because that model is sparsely activated under Instruction-Following Pruning, only a small subset of its experts occupies DRAM at any time, so the always-on tokenizer competes for the same memory, and its parameter count bears directly on power and latency. In this work we study how to compress such a tokenizer by distillation, taking as the supervision… Thu, 24 Sep 2026 00:00:00 GMT practical-recipe-federated-asr https://machinelearning.apple.com/research/practical-recipe-federated-asr Semi-supervised federated learning (SSFL) trains models on clients’ unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particularly fragile here: pseudo-label errors compound across the output sequence and across training rounds into divergence, leaving a large gap to fully-supervised FL. We show that closing this gap turns on two coupled design axes—the teacher (which model generates the pseudo-labels) and the anchor (the server-side updates on labeled data that stabilize training). On the teacher… Thu, 24 Sep 2026 00:00:00 GMT guide-language-flow https://machinelearning.apple.com/research/guide-language-flow We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to construct a guidance signal. This works using a similar principle as autoguidance, but eliminates the need for an additional forward pass at inference time and provides a reliable path to ensure that the weak and strong model share similar dynamics. We apply and benchmark this method on continuous diffusion language models, where probe guidance sets a new state-of-the-art performance on unconditional generation. When applied to a… Wed, 23 Sep 2026 00:00:00 GMT dynamically-scaled-activation-steering https://machinelearning.apple.com/research/dynamically-scaled-activation-steering Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected… Fri, 18 Sep 2026 00:00:00 GMT reversal-bench-rl-cliff https://machinelearning.apple.com/research/reversal-bench-rl-cliff A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend on underlying environmental reversibility, a property absent in real world manipulation, where events such as pushing objects off tables or spilling granular substances cannot be undone. We introduce REVERSAL-BENCH, a benchmark that controls reversibility via a continuous parameter ρ∈ [0, 1] and provides a reset oracle, a ground-truth verification mechanism to test state recoverability across eight manipulation settings in five physics engines… Thu, 17 Sep 2026 00:00:00 GMT shared-selective-persistent-memory https://machinelearning.apple.com/research/shared-selective-persistent-memory Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive—irrelevant context degrades generation quality. We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context—task specifications, data… Wed, 16 Sep 2026 00:00:00 GMT