论文检索

Reinforcement Learning · Everything Else

Zihan Liu, Zhuolin Yang, Yang Chen, Chankyu Lee, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

In this work, we investigate the synergy between supervised fine-tuning (SFT) and reinforcement learning (RL) in developing strong reasoning models. We begin by curating the SFT training data through two scaling strategies: increasing the number of collected prompts and the number of generated responses per prompt. Both approaches yield notable improvements in reasoning performance, with scaling the number of prompts resulting in more substantial gains. We then explore the following questions regarding the synergy between SFT and RL: (i) Does a stronger SFT model consistently lead to better final performance after large-scale RL training? (ii) How can we determine an appropriate sampling temperature during RL training to effectively balance exploration and exploitation for a given SFT initialization? Our findings suggest that (i) holds true, provided effective RL training is conducted, particularly when the sampling temperature is carefully chosen to maintain the temperature-adjusted entropy around 0.3, a setting that strikes a good balance between exploration and exploitation. Notably, the performance gap between initial SFT models narrows significantly throughout the RL process. Built on a strong SFT foundation and SFT–RL synergy, our AceReason-Nemotron-1.1 7B model significantly outperforms AceReason-Nemotron-1.0 and achieves new state-of-the-art performance among Qwen2.5-7B-based reasoning models on challenging math and code benchmarks, thereby demonstrating the effectiveness of our post-training recipe.

General Machine Learning · Everything Else

Maria-Eleni Sfyraki, Jun-Kun Wang

In this work, we revisit the problem of active sequential prediction-powered mean estimation, where at each round one must decide the query probability of the ground-truth label upon observing the covariates of a sample. Furthermore, if the label is not queried, the prediction from a machine learning model is used instead. Prior work proposed an elegant scheme that determines the query probability by combining an uncertainty-based suggestion with a constant probability that encodes a soft constraint on the query probability. We explored different values of the mixing parameter and observed an intriguing empirical pattern: the smallest confidence width tends to occur when the weight on the constant probability is close to one, thereby reducing the influence of the uncertainty-based component. Motivated by this observation, we develop a non-asymptotic analysis of the estimator and establish a data-dependent bound on its confidence interval. Our analysis further suggests that when a no-regret learning approach is used to determine the query probability and control this bound, the query probability converges to the constraint of the max value of the query probability when it is chosen obliviously to the current covariates. We also conduct simulations that corroborate these theoretical findings.

General Machine Learning · Everything Else

Hongyi Liu, Jiaji Huang, Zhen Jia, Youngsuk Park, Yu-Xiang Wang

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the best draft model in hindsight for each query in terms of either the token acceptance probability or expected acceptance length. In particular, we show that we can accurately evaluate all draft models, instead of only the chosen model without incurring additional queries to the target model, which allows us to improve exponentially over the existing bandit-based approach as the number of draft models increases. Our approach is generically applicable with any speculative decoding methods (single draft, multi-drafts and draft-trees). Moreover, we design system-efficient versions of online learners and demonstrate that the overhead in computation and latency can be substantially reduced. We conduct extensive experiments on open-source LLMs and diverse datasets, demonstrating that our methods substantially outperform the state-of-the-art EAGLE3 and the BanditSpec baseline in a variety of domains where specialized domain-expert drafters are available, especially when long reasoning chains are required.

Applications · Everything Else

Yunqing Liu, Nan Zhang, Zhiming Tan

Effective specification-aware part retrieval within complex CAD assemblies is essential for automated engineering tasks. However, using LLMs/VLMs for this task is challenging: the CAD model metadata sequences often exceed token budgets, and fine-tuning high-performing proprietary models (e.g., GPT or Gemini) is unavailable. Therefore, we need a framework that delivers engineering value by handling long, non-natural-language CAD model metadata using VLMs, but without training. We propose a 2-stage framework with inference-time adaptation that combines corrected Error Notebooks with RAG to substantially improve VLM-based part retrieval reasoning. Each Error Notebook is built by correcting initial CoTs through reflective refinement, and then filtering each trajectory using our proposed grammar-constraint (GC) verifier to ensure structural well-formedness. The resulting notebook forms a high-quality repository of specification-CoT-answer triplets, from which RAG retrieves specification-relevant exemplars to condition the model's inference. We additionally contribute a CAD dataset with human preference annotations. Experiments with proprietary models (GPT-4o, Gemini, etc) show large gains, with GPT-4o (Omni) achieving up to +23.4 absolute accuracy points on the human-preference benchmark. The proposed GC verifier can further produce up to +4.5 accuracy points. Our approach also surpasses other training-free baselines (standard few-shot learning, self-consistency) and yields substantial improvements also for open-source VLMs (Qwen2-VL-2B-Instruct, Aya-Vision-8B). Under the cross-model GC setting, where the Error Notebook is constructed using GPT-4o (Omni), the 2B model inference achieves performance that comes within roughly 4 points of GPT-4o mini.

Deep Learning · Everything Else

Olga Saukh, Dong Wang, Haris Šikić, Yun Cheng, Lothar Thiele

Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs a low-rank projection via weight clustering. We formalize both as orthogonal operators and show that, within a rank distance of one, folding provably yields smaller parameter reconstruction error, and under mild smoothness assumptions, smaller functional perturbations than pruning. At scale, we evaluate >1'000 checkpoints spanning ResNet18, PreActResNet18, ViT-B/32, and CLIP ViT-B/32 on CIFAR-10 and ImageNet-1K, covering diverse training hyperparameters (optimizers, learning rates, augmentations, regularization, sharpness-aware training). We show that folding typically achieves higher post-compression accuracy, with the largest gains at moderate–high compression. The gap narrows and occasionally reverses at specific training setups. Our results position folding as a geometry-aware, calibration-free alternative to pruning that is often superior in practice and principled in theory.

Applications · Everything Else

Hongrui Wang, Fan Zhang, Zhiyuan Yu, Ziya Zhou, Xi Chen, Can Yang, Yang Wang

Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attributes such as rhythmic stability and synchronization, leading to a focus on differences between tracks rather than their inherent properties. In this paper, we introduce SyncTrack, a synchronous multi-track waveform music generation model designed to capture the unique characteristics of multi-track music. SyncTrack features a novel architecture that includes track-shared modules to establish a common rhythm across all tracks and track-specific modules to accommodate diverse timbres and pitch ranges. Each track-shared module employs two cross-track attention mechanisms to synchronize rhythmic information, while each track-specific module utilizes learnable instrument priors to better represent timbre and other unique features. Additionally, we enhance the evaluation of multi-track music quality by introducing rhythmic consistency through three novel metrics: Inner-track Rhythmic Stability (IRS), Cross-track Beat Synchronization (CBS), and Cross-track Beat Dispersion (CBD). Experiments demonstrate that SyncTrack significantly improves the multi-track music quality by enhancing rhythmic consistency.

Deep Learning · Everything Else

Wenyu Mao, Shuchang Liu, HailanYang, Xiaobei Wang, Xiaoyu Yang, Xu Gao, Xiang Li, Lantao Hu, Han Li, Kun Gai 等

For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recommender calls a slower but more sophisticated reranking model that refines the item list exposure to the user. To consistently optimize the two-stage retrieval reranking framework, most efforts have focused on learning reranker-aware retrievers. In contrast, there has been limited work on how to achieve a retriever-aware reranker. In this work, we provide evidence that the retriever scores from the previous stage are informative signals that have been underexplored. Specifically, we first empirically show that the reranking task under the two-stage framework is naturally a noise reduction problem on the retriever scores, and theoretically show the limitations of naive utilization techniques of the retriever scores. Following this notion, we derive an adversarial framework DNR that associates the denoising reranker with a carefully designed noise generation module. The resulting DNR solution extends the conventional score error minimization loss with three augmented objectives, including: 1) a denoising objective that aims to denoise the noisy retriever scores to align with the user feedback; 2) an adversarial retriever score generation objective that improves the exploration in the retriever score space; and 3) a distribution regularization term that aims to align the distribution of generated noisy retriever scores with the real ones. We conduct extensive experiments on three public datasets and an industrial recommender system, together with analytical support, to validate the effectiveness of the proposed DNR.

Applications · Everything Else

Hang Zheng, Hongshen Xu, Yongkai LIN, Shuai Fan, Lu Chen, Kai Yu

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness—its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.

Social Aspects · Everything Else

Tianhao Li, Chuangxin Chu, Yujia Zheng, Bohan Zhang, Neil Gong, Chaowei Xiao

Multi-agent systems (MAS) built on large language models (LLMs) increasingly rely on agent-to-agent (A2A) protocols to enable capability discovery, task orchestration, and artifact exchange across heterogeneous stacks. While these protocols promise interoperability, they also introduce new vulnerabilities. In this paper, we present the first comprehensive security evaluation of A2A-MAS. We develop a taxonomy and threat model that categorize risks into supply-chain manipulations and protocol-logic weaknesses, and we detail six concrete attacks spanning all A2A stages and components with impacts on confidentiality, integrity, and availability. Building on this taxonomy, we introduce A2ASecBench, the first A2A-specific security benchmark framework capable of probing diverse and previously unexplored attack vectors. Our framework incorporates a dynamic adapter layer for deployment across heterogeneous agent stacks and downstream workloads, alongside a joint safety–utility evaluation methodology that explicitly measures the trade-off between harmlessness and helpfulness by pairing adversarial trials with benign tasks. We empirically validate our framework using official A2A Project demos across three representative high-stakes domains (travel, healthcare, and finance), demonstrating that the identified attacks are both pervasive and highly effective, consistently bypassing default safeguards. These findings highlight the urgent need for protocol-level defenses and standardized benchmarking to secure the next generation of agentic ecosystems.

Computer Vision · Everything Else

Zekai Deng, Ye Shi, Kaiyang Ji, Lan Xu, Shaoli Huang, Jingya Wang

Human-object interaction (HOI) synthesis is crucial for applications in animation, simulation, and robotics. However, existing approaches either rely on expensive motion capture data or require manual reward engineering, limiting their scalability and generalizability. In this work, we introduce the first unified physics-based HOI framework that leverages Vision-Language Models (VLMs) to enable long-horizon interactions with diverse object types — including static, dynamic, and articulated objects. We introduce VLM-Guided Relative Movement Dynamics (RMD), a fine-grained spatio-temporal bipartite representation that automatically constructs goal states and reward functions for reinforcement learning. By encoding structured relationships between human and object parts, RMD enables VLMs to generate semantically grounded, interaction-aware motion guidance without manual reward tuning. To support our methodology, we present Interplay, a novel dataset with thousands of long-horizon static and dynamic interaction plans. Extensive experiments demonstrate that our framework outperforms existing methods in synthesizing natural, human-like motions across both simple single-task and complex multi-task scenarios. For more details, please refer to our project webpage: https://vlm-rmd.github.io/.

Deep Learning · Everything Else

Gyeongje Cho, Yeonkyoung So, Jaejin Lee

Recent findings raise concerns about whether the evaluation of Multiple-Choice Question Answering (MCQA) accurately reflects the comprehension abilities of large language models. This paper explores the concept of \textit{choice sensitivity}, which refers to the tendency for model decisions to be more influenced by the answer options than by a genuine understanding of the question. We introduce a new scoring method called **Normalized Probability Shift by the Question (NPSQ)**, designed to isolate the impact of the question itself and provide a more reliable assessment of comprehension. Through experiments involving various input formats, including cloze, symbols, and hybrid formats, we find that traditional scoring methods — such as those based on log-likelihood or its length-normalized variant — are vulnerable to superficial characteristics of the answer choices. In contrast, NPSQ remains stable even when modifications are made to the answer options.

Applications · Everything Else

Marius Miron, David Robinson, Milad Alizadeh, Ellen Gilsenan-McMahon, Gagan Narula, Emmanuel Chemla, Maddie Cusimano, Felix Effenberger, Masato Hagiwara, Benjamin Hoffman 等

Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral studies. Many tasks in this field, such as species, individual, and behavior classification and detection, are well-suited to machine learning. However, they often suffer from limited annotated data, highlighting the need for a general-purpose bioacoustic encoder capable of extracting useful representations for diverse downstream tasks. Such encoders have been proposed before, but are often limited in scope due to a focus on a narrow range of species (typically birds), and a reliance on a single model architecture or training paradigm. Moreover, they are usually evaluated on a small set of tasks and datasets. In this work, we present a large-scale empirical study that covers aspects of bioacoustics that are relevant to research but have previously been scarcely considered: training data diversity and scale, model architectures and training recipes, and the breadth of evaluation tasks and datasets. We obtain encoders that are state-of-the-art on the existing and newly proposed benchmarks. We also identify *what matters* for training these encoders, such that this work can be extended when more data are available or better architectures are proposed. Specifically, across 26 datasets with tasks including species classification, detection, individual ID, and vocal repertoire discovery, we find that self-supervised pre-training followed by supervised post-training on a mixed bioacoustics + general-audio corpus yields the strongest in- and out-of-distribution performance. We show the importance of data diversity in both stages. To support ongoing research and applications, we release the model checkpoints as well as the Animal Vocalization Encoder library [AVEX](https://projects.earthspecies.org/avex/) (an API for model loading and inference, and a Python-based system for training and evaluating bioacoustics representation learning models)

Applications · Everything Else

Shufan Jiang, Sizhou Chen, Chi Zhang, Xiao-Lei Zhang, Xuelong Li

Creating an immersive and interactive theatrical experience is a long-term goal in the field of interactive narrative. The emergence of large language models (LLMs) provides a new path to achieve this goal. However, existing LLM-based drama generation methods often produce models that lack initiative and cannot interact with the physical scene, while typically requiring detailed user input that diminishes the immersion of live performance. To address these challenges, we propose HAMLET, a hierarchical adaptive multi-agent framework focused on drama creation and real-time online performance. Given a simple topic, the framework first generates a narrative blueprint to guide the subsequent improvisational performance. In the online performance phase, each actor is equipped with an adaptive reasoning module that enables decision-making based on their personas, memories, goals, and emotional states during complex group chat scenarios. Beyond dialogue, actor agents engage in embodied interactions by changing the state of scene props through actions such as opening a letter or picking up a weapon, which are broadcast to update the global environmental context. To objectively assess the quality of live embodied theatrics, we establish a comprehensive evaluation method and introduce HAMLETJudge, a specialized critic model for automated evaluation. Experimental results demonstrate that HAMLET excels in creating expressive, coherent, and physically interactive theatrical experiences in an autonomous manner.

Applications · Everything Else

Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, Adamenko Pavel, Ivan Lopatin, Alexey Kutalev, Dmitrii Babaev

LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can generalize across the diverse programming languages required in real-world software engineering. We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python. Multi-LCB transforms Python tasks from the LCB dataset into equivalent tasks in other languages while preserving LCB’s contamination controls and evaluation protocol. Because it is fully compatible with the original LCB format, Multi-LCB will automatically track future LCB updates, enabling systematic assessment of cross-language code generation competence and requiring models to sustain performance well beyond Python. We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting, language-specific contamination, and substantial disparities in multilingual performance. Our results establish Multi-LCB as a rigorous new benchmark for multi-programming-language code evaluation, directly addressing LCB’s primary limitation and exposing critical gaps in current LLM capabilities.

Reinforcement Learning · Everything Else

Zixuan Liu, Xiaolin Sun, Zizhan Zheng

Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them vulnerable to reward hacking, where high proxy returns arise from unintended or exploitative behaviors. Recent work formalizes this issue using r-correlation between proxy and true rewards, but existing methods like occupancy-regularized policy optimization (ORPO) optimize against a fixed proxy and do not provide strong guarantees against broader classes of correlated proxies. In this work, we formulate reward hacking as a robust policy optimization problem over the space of all r-correlated proxy rewards. We derive a tractable max-min formulation, where the agent maximizes performance under the worst-case proxy consistent with the correlation constraint. We further show that when the reward is a linear function of known features, our approach can be adapted to incorporate this prior knowledge, yielding both improved policies and interpretable worst-case rewards. Experiments across several environments show that our algorithms consistently outperform ORPO in worst-case returns, and offer improved robustness and stability across different levels of proxy–true reward correlation. These results show that our approach provides both robustness and transparency in settings where reward design is inherently uncertain.

Reinforcement Learning · Everything Else

Qinglong Hu, Tong Xialiang, Mingxuan Yuan, Fei Liu, Zhichao Lu, Qingfu Zhang

Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders real-world deployment. This work addresses this challenge by introducing a novel approach for programmatic control policy discovery, called **M**ultimodal Large **L**anguage Model-assisted **E**volutionary **S**earch (MLES). MLES utilizes multimodal large language models as programmatic policy generators, combining them with evolutionary search to automate policy generation. It integrates visual feedback-driven behavior analysis within the policy generation process to identify failure patterns and guide targeted improvements, thereby enhancing policy discovery efficiency and producing adaptable, human-aligned policies. Experimental results demonstrate that MLES achieves performance comparable to Proximal Policy Optimization (PPO) across two standard control tasks while providing transparent control logic and traceable design processes. This approach also overcomes the limitations of predefined domain-specific languages, facilitates knowledge transfer and reuse, and is scalable across various tasks, showing promise as a new paradigm for developing transparent and verifiable control policies. Code is publicly available at https://github.com/QingL2000/MLES.

Deep Learning · Everything Else

Hao Yi, Yulan Hu, Xin Li, Sheng Ouyang, Lizhong Ding, Yong Liu

Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate whether fewer but more informative queries can yield similar or superior performance, introducing active learning (AL) into RLVR. We identify that classic AL sampling strategies fail to outperform random selection in this setting, due to ignoring \textbf{objective uncertainty} when only selecting by subjective uncertainty. This work proposes an \textbf{uncertainty consistency} metric to evaluate how well subjective uncertainty aligns with objective uncertainty. In the offline setting, this alignment is measured using the Point-Biserial Correlation Coefficient (PBC). For online training, because of limited sampling and dynamically shifting output distributions, PBC estimation is difficult. Therefore, we introduce a new online variant, computed from normalized advantage and subjective uncertainty. Theoretically, we prove that the online variant is strictly negatively correlated with offline PBC and supports better sample selection. Experiments show our method consistently outperforms random and classic AL baselines, achieving full-dataset performance while training on only 30\% of the data, effectively reducing the cost of RLVR for reasoning tasks.\footnote{The code is available at \hyperref[https://github.com/yihao-123/uncertainty-consistency]{https://github.com/yihao-123/uncertainty-consistency}. }

General Machine Learning · Everything Else

Maolin WANG, Zhiqi Li, Binhao Wang, Xuhui Chen, Tianshuo Wei, Wanyu Wang, Shikai Fang, Ruocheng Guo, Zenglin Xu, Xiangyu Zhao

Analyzing dynamic tensor streams is fundamentally challenged by complex, evolving temporal dynamics and the need to identify informative data from high-velocity streams. Existing methods often lack the expressiveness to model multi-scale temporal dependencies, limiting their ability to capture evolving patterns. We propose SONATA, a novel framework that unifies expressive dynamic embedding modeling with adaptive coreset selection. SONATA leverages principled machine learning techniques for efficient evaluation of each observation for uncertainty, novelty, influence, and information gain, and dynamically prioritizes learning from the most valuable data using Bellman-inspired optimization. Entity dynamics are modeled with Linear Dynamical Systems and expressive temporal kernels for fine-grained temporal representation. Experiments on synthetic and real-world datasets show that SONATA consistently outperforms state-of-the-art methods in modeling complex temporal patterns and improving predictive accuracy for dynamic tensor streams.

Reinforcement Learning · Everything Else

Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Bilgin, Ollie Liu, Willie Neiswanger

How cost-effectively can strong reasoning abilities be achieved in language models? Driven by this question, we present Tina, a family of tiny reasoning models achieved with high cost-efficiency. Tina shows that substantial reasoning performance can be developed using only minimal resources, by applying low-rank adaptation (LoRA) during reinforcement learning (RL), to an already tiny 1.5B parameter base model. This minimalist approach produces models that are competitive with, and sometimes surpass, SOTA RL reasoning models built upon the same base model. Crucially, this is achieved at a tiny fraction of the computational cost employed by existing models. In fact, the best Tina model achieves a >20\% reasoning performance increase and 43.33\% zero-shot Pass@1 accuracy on AIME24, at only \$9 USD cost (i.e., an estimated 260x reduction). Our work reveals the surprising effectiveness of efficient RL reasoning via LoRA. We validate this across multiple open-source reasoning datasets and various ablation settings starting with a single, fixed set of hyperparameters. Furthermore, we explore the hypothesis that this effectiveness and efficiency stem from LoRA rapidly adapting the model to the structural format of reasoning rewarded by RL, while largely preserving the base model's underlying knowledge. In service of accessibility and open research, we fully open-source all code, training logs, model weights, and checkpoints.

Deep Learning · Everything Else

Wenyuan Liu, Haoqian Meng, Yilun Luo, Peng Zhang, Xindian Ma

Quantization significantly accelerates inference in large language models (LLMs) by replacing original high-precision matrices with low-precision counterparts. Recent advances in weight-activation quantization have primarily focused on mapping both weights and activations to the INT4 format. Although the new FP4 Tensor Cores in NVIDIA’s Blackwell architecture offer up to 4$\times$ speedup over FP16, existing INT4-based kernels fail to fully exploit this capability due to mismatched data formats. To bridge this gap, we propose MicroMix, a co-designed mixed-precision quantization algorithm and GEMM kernel based on Microscaling (MX) data formats. Tailored for the Blackwell architecture, the MicroMix kernel supports arbitrary combinations of MXFP4, MXFP6, and MXFP8 channels, and produces BFloat16 outputs. To achieve a favorable trade-off between accuracy and efficiency for each linear layer, we introduce quantization thresholds that identify activation elements where lower-precision formats (MXFP4 or MXFP6) incur excessive quantization error. Our algorithm selectively allocates higher-precision channels to preserve accuracy while maintaining compute efficiency. On the Llama and Qwen model families, MicroMix achieves near-FP16 performance across diverse downstream tasks with an average precision of 5 bits. In particular, Qwen2.5-32B-Base, Coder and Math exhibit lossless accuracy on zero-shot, code generation, and mathematical reasoning benchmarks. In addition, on RTX 5070Ti laptop and RTX 5090 GPUs, our kernel achieves 2.29-3.38$\times$ acceleration compared to TensorRT-FP16. Our code is available at https://github.com/lwy2020/MicroMix.