arXiv subjects

Mingyuan Ma

Publications and source records attributed to Mingyuan Ma.

At least 19 recordsLinked to original sources

arXiv2026

Bilateral Protection for Private LoRA Inference with Intel TDX

Cloud services using private low-rank adaptation (LoRA) must protect client inputs and outputs alongside owners' proprietary parameters and execute the approved adaptation. We design and implement a system for bilateral protection of private LoRA inference using Intel Trust Domain Extensions (TDX), connecting approved application identity to actual artifact consumption and adapter activation. The client and LoRA owner independently verify remote attestation, application identity, and binding to the actual Transport Layer Security (TLS) public key before releasing inputs and the weight-decryption key. A fixed read-only image and verified-byte consumption connect approved identities to inference objects, with all inference inside a trust domain. Experiments on real TDX hardware reject controlled application and boot-parameter modifications before secret release. Across 400 fixed dialogues, protected and native CPU inference in the same trust domain produce identical token sequences for all 400 pairs. Across 12 independent trust-domain boots, the steady-state service-to-native time ratio is 1.0094, with a 95% interval of [1.0064, 1.0126]. The system connects bilateral secret release, approved model use, and task-capability preservation, providing verifiable implementation and cost evidence for confidential inference with a public base and private adapter.

cs.CR↗

arXiv2026

Magnetic control of reflectionless states and an intrinsic-mode exceptional point in a magnon-phonon coupling system

Reflectionless states (RLs) and exceptional points (EPs) are hallmark singular responses of non-Hermitian systems, with potential applications in sensing, wave control, and energy manipulation. Yet, realizing and independently tuning these states in a compact integrated platform remains challenging. Here, we demonstrate two-dimensional magnetic control of RLs and EPs in an on-chip magnon-phonon system based on a FeGaB-32 degree-YX-LiNbO3 heterostructure. The magnetic-field magnitude tunes the magnon-phonon detuning, driving a low-loss reflection zero across the real-frequency axis and producing two field-tunable RLs with near-vanishing reflection. A closed contour of the experimentally measured complex S11 around the reflection-zero singularity accumulates a -2pi phase winding. Independently, rotating the magnetic field tunes the magnon-phonon coupling strength, driving the intrinsic magnon-phonon eigenmode spectrum across an exceptional point, identified by the exchange between real-part and imaginary-part eigenvalue splitting. A unified one-port input-output model connects the measured complex S11 response to the field-driven dynamics of the reflection zeros and the angle-tuned intrinsic magnon-phonon eigenmodes. These results establish a magnetically programmable non-Hermitian magnon-phonon platform for integrated wave control and compact vector magnetic sensing.

cond-mat.mtrl-sci↗

arXiv2026

Nemotron 3.5 Bolt 74B-A9B 24GB: A Hybrid Vision-Language Model for Local AI

We introduce Nemotron 3.5 Bolt 74B-A9B 24GB, a hybrid Mamba-Transformer vision-language model that optimizes speed and intelligence per GB of memory used for local agentic workloads. Derived from the Nemotron 3.5 Super VL 120B-A12B model family, Nemotron 3.5 Bolt 74B-A9B 24GB combines Star Elastic compression with 2-bit Quantization-Aware Distillation for memory-constrained deployment. The model is optimized for reasoning, agentic tool use, and web & terminal interactions. We also trained a LiLiCorr speculative drafter that is released alongside the model to reach our target inference speed. The resulting model achieves a higher accuracy than leading models with similar memory footprints and speed across many benchmarks for general agentic capabilities (e.g., GDPVal v2), web browsing (e.g., BrowseComp), and terminal use (e.g., Terminal-Bench 2.1), with a relatively high TPS of 84 on RTX Spark that is comparable to models with much lower active parameter counts and more than sufficient for long-horizon agentic applications.

cs.CV↗

arXiv2026

Field-free Magnetoacoustic Nonreciprocity via Exchange-bias Engineering

Nonreciprocal wave propagation is essential for directional signal processing and isolation. Magnetoacoustic systems are attractive platforms for nonreciprocal devices because of their small footprint and passive operation. However, pronounced nonreciprocity typically requires an external bias field,limiting device miniaturization and integration. Here, we demonstrate field-free magnetoacoustic nonreciprocity in an IrMn/FeGaB/Cu/FeGaB multilayer integrated with a shear-horizontal-wave delay line. Exchange-bias engineering stabilizes a remanent magnetic state with broken time-reversal and spatial-inversion symmetries while tailoring the spin-wave dispersion to achieve resonant magnetoacoustic coupling at zero field. The normalized isolation reaches 21 dB/mm, with its sign programmable by the field-sweep history. Further numerical optimization predicts a zero-field normalized isolation of 91 dB/mm by increasing the dynamical magnetic asymmetry. Our work establishes exchange-bias engineering as a promising route toward compact RF isolators and circulators and as a general strategy for realizing magnetoacoustic devices without external magnetic fields.

cond-mat.mtrl-sci↗

arXiv2026

Automated Instruction Encoding Synthesis for Modern GPU ISA Compression

Modern GPU kernels increasingly stress the instruction supply path, while fixed instruction containers can leave substantial footprint slack. This paper presents an automated encoding-synthesis framework that treats instruction layout as a constrained slot-assignment problem over a validated instruction-form field specification. The formulation separates semantic field identity from physical bit positions and supports tied, pinned, and free placement constraints, making it applicable when recurring decoded fields are not frozen by a public format contract. We instantiate the framework for NVIDIA SASS: raw public encoding text is normalized into a machine-readable specification, a SASS disassembler is validated against nvdisasm on 3.78M instructions, released as an open benchmark, and CP-SAT synthesis is used for fixed-length and variable-length encodings. On 142 Blackwell kernel inputs, variable-length synthesis reduces instruction footprint by 33%, with comparable reductions after re-synthesis on Ampere and Hopper; fixed-length synthesis on the same specification reduces decoder area by 16% against a decoder generated from the NVIDIA-observed 128-bit layout by the same generator and flow. Generated fetch/decode RTL meets 1.5 GHz in TSMC 22 nm with a replicated area delta of 0.12% of a GA100-class die; a same-node SRAM comparison shows the footprint reduction corresponds to about 9x this added logic in instruction-SRAM bit-cell area.

cs.AR↗

arXiv2026

Octopus: On-device language model for function calling of software APIs

In the rapidly evolving domain of artificial intelligence, Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs. We meticulously compile a dataset derived from software API documentation and apply fine-tuning to LLMs with capacities of 2B, 3B and 7B parameters, specifically to enhance their proficiency in software API interactions. Our approach concentrates on refining the models' grasp of API structures and syntax, significantly enhancing the accuracy of API function calls. Additionally, we propose \textit{conditional masking} techniques to ensure outputs in the desired formats and reduce error rates while maintaining inference speeds. We also propose a novel benchmark designed to evaluate the effectiveness of LLMs in API interactions, establishing a foundation for subsequent research. Octopus, the fine-tuned model, is proved to have better performance than GPT-4 for the software APIs calling. This research aims to advance automated software development and API integration, representing substantial progress in aligning LLM capabilities with the demands of practical software engineering applications.

cs.CL↗

arXiv2026

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Analysis of production traces reveals a dynamic bursty-group pattern in which sets of models become active together and shift over time; existing space- and time-sharing approaches lack principled mechanisms to adapt to this variability, forcing trade-offs between SLO adherence and efficiency. We observe that elastic memory allocation can unify spatial and temporal sharing. Based on this insight, we have developed Prism, a memory-centric LLM co-serving framework that applies memory ballooning to reclaim memory across models and support both forms of sharing under a single scheme. Prism's balloon driver, referred to as kvcached, has been open-sourced at https://github.com/ovg-project/kvcached, and deployed in production environments across 10K+ GPUs.

cs.DC↗

arXiv2026

ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Training-free acceleration methods reduce latency by either sparsifying the model architecture or shortening the sampling trajectory. Current training-free acceleration methods are more complex than necessary: higher-order predictors amplify error under aggressive speedups, and architectural modifications hinder deployment. Beyond 2x acceleration, step skipping creates structural scarcity -- at most one fresh evaluation per local window -- leaving the computed output and its backward difference as the only causally grounded information. Based on this, we propose ZEUS, an acceleration method that predicts reduced denoiser evaluations using a second-order predictor, and stabilizes aggressive consecutive skipping with an interleaved scheme that avoids back-to-back extrapolations. ZEUS adds essentially zero overhead, no feature caches, and no architectural modifications, and it is compatible with different backbones, prediction objectives, and solver choices. Across image and video generation, ZEUS consistently improves the speed-fidelity performance over recent training-free baselines, achieving up to 3.2x end-to-end speedup while maintaining perceptual quality. Our code is available at: https://github.com/Ting-Justin-Jiang/ZEUS.

cs.LG↗

arXiv2026

The average order of a connected vertex set in $K_m \times P_n$

Let $G$ be a connected graph. Let $N(G)$ and $S(G)$ be the number of connected sets of $G$ and the sum of the orders of these connected sets of $G$, respectively. Then $A(G)=\frac{S(G)}{N(G)}$ is called the average order of a connected set of $G$. In this paper, we derive a closed-form formula for $A(K_m \times P_n)$, where $K_m \times P_n$ is the Cartesian product of the complete graph $K_m$ and the path $P_n$.

math.CO↗

arXiv2026

Budgeted Active Experimentation for Treatment Effect Estimation from Observational and Randomized Data

Estimating heterogeneous treatment effects is central to data-driven decision-making, yet industrial applications often face a fundamental tension between limited randomized controlled trial (RCT) budgets and abundant but biased observational data collected under historical targeting policies. Although observational logs offer the advantage of scale, they inherently suffer from severe policyinduced imbalance and overlap violations, rendering standalone estimation unreliable. We propose a budgeted active experimentation framework that iteratively enhances model training for causal effect estimation via active sampling. By leveraging observational priors, we develop an acquisition function targeting uplift estimation uncertainty, overlap deficits, and domain discrepancy to select the most informative units for randomized experiments. We establish finite-sample deviation bounds, asymptotic normality via martingale Central Limit Theorems (CLTs), and minimax lower bounds to prove information-theoretic optimality. Extensive experiments on industrial datasets demonstrate that our approach significantly outperforms standard randomized baselines in cost-constrained settings.

stat.ME↗

arXiv2026

Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments

We study uplift estimation for combinatorial treatments. Uplift measures the pure incremental causal effect of an intervention (e.g., sending a coupon or a marketing message) on user behavior, modeled as a conditional individual treatment effect. Many real-world interventions are combinatorial: a treatment is a policy that specifies context-dependent action distributions rather than a single atomic label. Although recent work considers structured treatments, most methods rely on categorical or opaque encodings, limiting robustness and generalization to rare or newly deployed policies. We propose an uplift estimation framework that aligns treatment representation with causal semantics. Each policy is represented by the mixture it induces over contextaction components and embedded via a permutation-invariant aggregation. This representation is integrated into an orthogonalized low-rank uplift model, extending Robinson-style decompositions to learned, vector-valued treatments. We show that the resulting estimator is expressive for policy-induced causal effects, orthogonally robust to nuisance estimation errors, and stable under small policy perturbations. Experiments on large-scale randomized platform data demonstrate improved uplift accuracy and stability in long-tailed policy regimes

stat.ME↗

arXiv2026

Cohesive Group Discovery in Interaction Graphs under Explicit Density Constraints

Discovering cohesive groups is a fundamental primitive in graph-based recommender systems, underpinning tasks such as social recommendation, bundle discovery, and community-aware modeling. In interaction graphs, cohesion is often modeled as the $γ$-quasi-clique, an induced subgraph whose internal edge density meets a user-defined threshold $γ$. This formulation provides explicit control over within-group connectivity while accommodating the sparsity inherent in real-world data. This paper presents EDQC, an effective framework for cohesive group discovery under explicit density constraints. EDQC leverages a lightweight energy diffusion process to rank vertices for localizing promising candidate regions. Guided by this ranking, the framework extracts and refines a candidate subgraph to ensure the output strictly satisfies the target density requirement. Extensive experiments on 75 real-world graphs across varying density thresholds demonstrate that EDQC identifies the largest mean $γ$-quasi-cliques in the vast majority of cases, achieving lower variance than the state-of-the-art methods while maintaining competitive runtime. Furthermore, statistical analysis confirms that EDQC significantly outperforms the baselines, underscoring its robustness and practical utility for cohesive group discovery in graph-based recommender systems.

cs.SI↗

arXiv2025

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Multi-agent large language model (LLM) systems are increasingly adopted for complex language processing tasks that require communication and coordination among agents. However, these systems often suffer substantial overhead from repeated reprocessing of overlapping contexts across agents. In typical pipelines, once an agent receives a message from its predecessor, the full context-including prior turns-must be reprocessed from scratch, leading to inefficient processing. While key-value (KV) caching is an effective solution for avoiding redundant computation in single-agent settings where prefixes remain unchanged, it cannot be directly reused in multi-agent scenarios due to diverging prefixes introduced by agent-specific context extensions. We identify that the core challenge lies in the offset variance of KV-caches across agents. To address this, we propose KVCOMM, a training-free framework that enables efficient prefilling in multi-agent inference by reusing KV-caches and aligning cache offsets of overlapping contexts under diverse prefix contexts. KVCOMM estimates and adjusts KV-caches for shared content by referencing a pool of cached examples-termed anchors-that store observed cache deviations under varying prefixes. The anchor pool is maintained and updated online, allowing dynamic adaptation to distinct user requests and context structures. KVCOMM achieves over 70% reuse rate across diverse multi-agent workloads, including retrieval-augmented generation, math reasoning, and collaborative coding tasks, all without quality degradation. Particularly, when each fully-connected agent receives 1K input tokens with 512 prefix tokens and 512 output tokens under a five-agent setting, KVCOMM achieves up to 7.8x speedup compared to the standard prefill pipeline, reducing TTFT from ~430 ms to ~55 ms.

cs.MA↗

arXiv2025

Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration

Calibrating large-scale camera arrays, such as those in dome-based setups, is time-intensive and typically requires dedicated captures of known patterns. While extrinsics in such arrays are fixed due to the physical setup, intrinsics often vary across sessions due to factors like lens adjustments or temperature changes. In this paper, we propose a dense-feature-driven multi-frame calibration method that refines intrinsics directly from scene data, eliminating the necessity for additional calibration captures. Our approach enhances traditional Structure-from-Motion (SfM) pipelines by introducing an extrinsics regularization term to progressively align estimated extrinsics with ground-truth values, a dense feature reprojection term to reduce keypoint errors by minimizing reprojection loss in the feature space, and an intrinsics variance term for joint optimization across multiple frames. Experiments on the Multiface dataset show that our method achieves nearly the same precision as dedicated calibration processes, and significantly enhances intrinsics and 3D reconstruction accuracy. Fully compatible with existing SfM pipelines, our method provides an efficient and practical plug-and-play solution for large-scale camera setups. Our code is publicly available at: https://github.com/YJJfish/Multi-Cali-Anything

cs.CV↗

arXiv2025

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both offering promising solutions to enhance efficiency. Recently, these two sparsity paradigms have evolved largely in parallel, fostering the prevailing assumption that they function independently. However, a fundamental yet underexplored question remains: Do they truly operate in isolation, or is there a deeper underlying interplay that has yet to be uncovered? In this paper, we conduct the first comprehensive investigation into this question. By introducing and analyzing the matching mechanism between Core Neurons and Core Tokens, we found that key neurons and tokens for inference mutually influence and reinforce each other. Building on this insight, we propose CoreMatching, a co-adaptive sparse inference framework, which leverages the synergy between token and neuron sparsity to enhance inference efficiency. Through theoretical analysis and efficiency evaluations, we demonstrate that the proposed method surpasses state-of-the-art baselines on ten image understanding tasks and three hardware devices. Notably, on the NVIDIA Titan Xp, it achieved 5x FLOPs reduction and a 10x overall speedup. Code is released at https://github.com/wangqinsi1/2025-ICML-CoreMatching/tree/main.

cs.LG↗

arXiv2025

ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning

Low-Rank Adaptation (LoRA) has become a widely adopted technique for fine-tuning large-scale pre-trained models with minimal parameter updates. However, existing methods rely on fixed ranks or focus solely on either rank pruning or expansion, failing to adapt ranks dynamically to match the importance of different layers during training. In this work, we propose ElaLoRA, an adaptive low-rank adaptation framework that dynamically prunes and expands ranks based on gradient-derived importance scores. To the best of our knowledge, ElaLoRA is the first method that enables both rank pruning and expansion during fine-tuning. Experiments across multiple benchmarks demonstrate that ElaLoRA consistently outperforms existing PEFT methods across different parameter budgets. Furthermore, our studies validate that layers receiving higher rank allocations contribute more significantly to model performance, providing theoretical justification for our adaptive strategy. By introducing a principled and adaptive rank allocation mechanism, ElaLoRA offers a scalable and efficient fine-tuning solution, particularly suited for resource-constrained environments.

cs.LG↗

arXiv2025

Training Video Foundation Models with NVIDIA NeMo

Video Foundation Models (VFMs) have recently been used to simulate the real world to train physical AI systems and develop creative visual experiences. However, there are significant challenges in training large-scale, high quality VFMs that can generate high-quality videos. We present a scalable, open-source VFM training pipeline with NVIDIA NeMo, providing accelerated video dataset curation, multimodal data loading, and parallelized video diffusion model training and inference. We also provide a comprehensive performance analysis highlighting best practices for efficient VFM training and inference.

cs.CV↗

arXiv2024

A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models

The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality. These models are increasingly integrated into diverse applications, impacting both research and industry. However, their development and deployment present substantial challenges, including the need for extensive computational resources, high energy consumption, and complex software optimizations. Unlike traditional deep learning systems, LLMs require unique optimization strategies for training and inference, focusing on system-level efficiency. This paper surveys hardware and software co-design approaches specifically tailored to address the unique characteristics and constraints of large language models. This survey analyzes the challenges and impacts of LLMs on hardware and algorithm research, exploring algorithm optimization, hardware design, and system-level innovations. It aims to provide a comprehensive understanding of the trade-offs and considerations in LLM-centric computing systems, guiding future advancements in AI. Finally, we summarize the existing efforts in this space and outline future directions toward realizing production-grade co-design methodologies for the next generation of large language models and AI systems.

cs.AR↗