LEV is a decision model that performs reasoning by looping its layers instead of generating text, allowing it to deepen its computation on a per-question basis. Trained jointly across all loop steps, a single LEV checkpoint can answer at any depth, improving accuracy—especially on hard questions—while keeping inference fast. On benchmark tests, LEV outperforms dense and cascade models by 5.4 to 8.8 accuracy points with sub‑50 ms latency, and on‑demand depth selection saves 15–24% of computation for minimal accuracy loss.
arXiv:2610.07730v1 Announce Type: cross Abstract: Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a...
arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.
The paper introduces Elastic Latent Recurrence (ELR), a training recipe that enables looped language models to match the accuracy of non-recurrent models at a single loop while allowing additional loops to improve accuracy with more compute. ELR achieves this through gated state updates with learned step sizes, mixed loop counts during training, and conditioning on loop index and budget. The method also reduces training and inference overhead in Mixture-of-Experts models and produces a single checkpoint, Koi‑4B, that performs competitively with state‑of‑the‑art models on multiple benchmarks.
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the...
The paper introduces APEX, a learned controller that improves speculative decoding for large language models by dynamically selecting the best speculation strategy and adjusting draft depth during generation. APEX uses request‑level routing among EAGLE‑3, n‑gram, and draft‑model speculation, and block‑level depth adaptation based on causal decoding signals and verifier feedback. Integrated into vLLM and tested with Qwen3‑8B, APEX achieves up to 5.24× speedup over autoregressive decoding while reducing wasted tokens by 41% compared to fixed‑depth n‑gram speculation.
The paper introduces GLANCE, a one‑pass block drafting method that enables lossless speculative decoding for vision‑language models. By using a block‑diffusion head that reads the fused vision‑language state, GLANCE eliminates the need for the drafter to process the image at every step, allowing it to fill an entire block in a single forward pass. Experiments show that GLANCE can decode up to 2.93× faster than autoregressive decoding while maintaining exact greedy decoding results across multiple tasks.
The paper introduces Galahad, a memory layer that stores a transformer language model’s key‑value state for blocks of text, allowing subsequent requests to reuse previously computed attention rather than recomputing it. On seven real‑world datasets, 98.7% of prompt tokens were already read, and with Galahad the model could attend to an entire 97,000‑token corpus, achieving 98–100% recall on a 100‑fact test while reducing inference time and energy consumption dramatically. The approach was validated across 30 models and all runtimes, demonstrating that stateful inference can replace stateless serving without loss of accuracy.
arXiv:2609.38006v1 Announce Type: new Abstract: Running a language model locally offers advantages in privacy, latency, and cost, but local hardware fits only small models, which are less capable tha...
arXiv:2610.15501v1 Announce Type: new Abstract: Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does...
arXiv:2609.23886v1 Announce Type: new Abstract: Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears wit...
A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out...
System1-Arena is a benchmark that evaluates which decisions can be handled by System‑1 models—those that output probabilities in a single forward pass—versus System‑2 models that generate reasoning steps. It contains 92,000 questions across 105 tasks from 268 public sources, grouped into text classification, applied decisions, evaluation and control, and agent/action, and also includes 138 closed‑loop environments such as web shopping, coding control, robotics, games, and driving. The study tests 30 models, showing that large System‑1 models can match or exceed fast closed LLMs in non‑agentic accuracy with better‑calibrated probabilities at lower latency, while reasoning LLMs are most accurate but far more expensive, and large open LLMs perform best in closed‑loop settings.