Osprey is a target‑agnostic pre‑training method that bootstraps draft models for speculative decoding from existing small language models. By pruning to a shallow backbone, restoring language‑modeling capability with next‑token pretraining, and adapting via vocabulary alignment and distillation, Osprey reduces per‑target work to a lightweight adaptation step. Experiments show that a single Osprey backbone improves mean acceptance length by up to 22.7% and increases tokens per second by 17.5% across several large target models, especially on out‑of‑domain and multilingual data.
By Fengxiang Bie, Yuqing Jian, Yifan Yu, Zhongzhu Zhou, Zelei Shao, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu, Tianyi Zhang
arXiv:2610.14576v1 Announce Type: new
Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities...
By Keegan Wang
Verification-Aware Training (VAT) is a plug‑in framework that improves speculative decoding for large language models by simulating verification during training and using the resulting accept/reject patterns as supervision. VAT adds a lightweight binary verification head to predict whether each draft token will survive sequential verification, and replaces the fixed per‑position weighting with a verification‑adaptive schedule that keeps full weight up to the first rejection point. When applied to EAGLE‑3 and DFlash on Qwen3‑4B, Qwen3‑8B, and LLaMA‑3.1‑8B, VAT increases average acceptance length by up to 11.4% and wall‑clock speedup by up to 8.7%, yielding consistent gains across math, code, and chat benchmarks.
By Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang, Sangmin Lee, Sangdoo Yun, Dongyoon Han
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.
By Manvi Jha, Zach Zhang, Zhichao Xu, Linbo Liu, Sai Muralidhar Jayanthi, Vinayak Arannil
arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.
By Didula Samaraweera, Anjana Supun, Srinath Perera
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
By Dengke Han
Intern-Decision is a family of multimodal decision models (0.8B, 2B, and 4B parameters) that output structured choices and candidate probabilities directly from text and optional images, avoiding the latency of free‑form responses. The models use an autoregressive masked language modeling objective, placing one decision placeholder per field in a complete assistant JSON skeleton, and evaluate all fields in a single causal forward pass. The 4B variant achieves 90.02 % unweighted average accuracy across seven evaluation suites, with a mean latency of 44.16 ms on an RTX 4090 for a 289‑token request, and shows improved calibration and accuracy when combined with temperature scaling and confidence‑based handoff.
By Tong Zhu, Zhe Xu, Zefeng He, Yunkai Chai, Xuyang Hu, Dehong Zheng, Yun Luo, Yafu Li, Qi Zhang, Yu Cheng
SWE-VERIFIER is a lightweight generative model that selectively triggers candidate sampling and verification for coding agents, scoring proposed actions to decide when additional sampling is needed and ranking the resulting actions before execution. Trained on Qwen3.5-4B with preference data, it improves resolution on MiniMax-M2.7 from 75.47% to 77.20% at 1.09× cost and on DeepSeek-V4-Flash from 72.60% to 74.27% at 1.13× cost, while verifying fewer than 4% of steps. The approach demonstrates that selective sampling and lightweight verification can enhance coding‑agent performance and inference efficiency with minimal overhead.
By Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang, Naihao Deng, Longju Bai, Jiaxin Pei, Rada Mihalcea, Lu Wang
Intern-Decision introduces 0.8B, 2B, and 4B multimodal decision models that output structured choices and probabilities directly from text and optional images, avoiding the latency of free‑form responses. The models use an autoregressive masked language modeling objective, placing decision placeholders in a JSON skeleton and evaluating all fields in a single causal pass. The 4B variant attains 90.02% unweighted accuracy across seven benchmarks, with sub‑45 ms latency on an RTX 4090, and demonstrates improved calibration and handoff performance in pilot studies.
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.
By Dhruv Saini, Rohan Pandey
The paper introduces EvoResearcher, a training‑free, inference‑time protocol that enables a frozen large language model to perform cost‑bounded self‑reflection and early stopping. By iterating through generate → self‑critique → revise steps until a maximum depth or a CONFIRMED sentinel is reached, the model can self‑verify its answers within a strict compute budget. The protocol incorporates four self‑reflective meta‑reward components—correctness, efficiency, reflection depth, and tool‑call diversity—implemented as prompt‑level mechanisms, and is validated on Big‑Bench Hard, GSM8K, and MATH benchmarks, achieving comparable accuracy while terminating 82‑88% of items early with only about 2.1 generations per question.
By Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li
arXiv:2609.36115v1 Announce Type: new
Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-criti...
By Shenghong Dai, Shiva Kumar Pentyala, Yingchi Liu, Shubham Mehrotra, Suman Banerjee, James Zhu, Bin Bi, Sitaram Asur, Phil Mui