Searcharxiv⌕ Search

arXiv subjects

Ang Li

Publications and source records attributed to Ang Li.

At least 109 records · Page 6Linked to original sources
arXiv2026

MoEless: Efficient MoE LLM Serving via Serverless Computing

Large Language Models (LLMs) have become a cornerstone of AI, driving progress across diverse domains such as content creation, search and recommendation systems, and AI-assisted workflows. To alleviate extreme training costs and advancing model scales, Mixture-of-Experts (MoE) has become a popular backbone for modern LLMs, which are commonly served in distributed deployment using expert parallelism (EP). However, MoE's sparse activation mechanism leads to severe expert load imbalance, where a few experts become overloaded while others remain idle, resulting in expert stragglers that inflate inference latency and serving cost. Existing expert load balancing solutions assume static resource configurations on serverful infrastructures, limiting expert scalability and elasticity, and resulting in either costly real-time expert swapping or degraded generation quality. We present MoEless, the first serverless MoE serving framework that mitigates expert load imbalance and accelerates inference via serverless experts. MoEless employs lightweight, layer-aware predictors to accurately estimate incoming expert load distributions and proactively identify stragglers. We design optimized expert scaling and placement strategies to maximize function locality, improve GPU utilization, and balance loads across experts and GPUs. MoEless is prototyped on top of Megatron-LM and deployed on an eight-GPU testbed. Experiments with open-source MoE models and real-world workloads show that MoEless reduces inference latency by 43% and inference cost by 84% compared to state-of-the-art solutions.

cs.DC↗
arXiv2026

AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents

Electronic Design Automation (EDA) remains heavily reliant on tool command language (Tcl) scripting to drive complex RTL-to-GDSII flows. This scripting-based paradigm is labor-intensive, error-prone, and difficult to scale across large design projects. Recent advances in large language models (LLMs) suggest a new paradigm of natural language-driven automation. However, existing EDA efforts remain limited and face key challenges, including the absence of standardized interaction protocols and dependence on external APIs that introduce privacy risks. We present AutoEDA, a framework that leverages the Model Context Protocol (MCP) to enable end-to-end natural language control of RTL-to-GDSII design flows. AutoEDA introduces MCP-based servers for task decomposition, tool selection, and automated error handling, ensuring robust interaction between LLM agents and EDA tools. To enhance reliability and confidentiality, we integrate locally fine-tuned LLM agents. We further contribute a benchmark generation pipeline for diverse EDA scenarios and extend CodeBLEU with Tcl-specific enhancements for domain-aware evaluation. Together, these contributions establish a comprehensive framework for LLM-driven EDA automation, bridging natural language interfaces with modern chip design flows. Empirical results show that AutoEDA achieves up to 9.9 times higher accuracy than naive approaches while reducing token usage by approximately 97% compared to in-context learning.

cs.AI↗
arXiv2026

A Robotic Testing Platform for Pipelined Discovery of Resilient Soft Actuators

Short lifetime under high electrical fields hinders the widespread robotic application of linear dielectric elastomer actuators (DEAs). Systematic scanning is difficult due to time-consuming per-sample testing and the high-dimensional parameter space affecting performance. To address this, we propose an optimization pipeline enabled by a novel testing robot capable of scanning DEA lifetime. The robot integrates electro-mechanical property measurement, programmable voltage input, and multi-channel testing capacity. Using it, we scanned the lifetime of Elastosil-based linear actuators across parameters including input voltage magnitude, frequency, electrode material concentration, and electrical connection filler. The optimal parameter combinations improved operational lifetime under boundary operating conditions by up to 100% and were subsequently scaled up to achieve higher force and displacement output. The final product demonstrated resilience on a modular, scalable quadruped walking robot with payload carrying capacity (>100% of its untethered body weight, and >700% of combined actuator weight). This work is the first to introduce a self-driving lab approach into robotic actuator design.

cs.RO↗
arXiv2026

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

cs.CL↗
arXiv2026

ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models

Vision-Language-Action (VLA) models enable instruction-following robotic manipulation, but they are typically pretrained on 2D data and lack 3D spatial understanding. An effective approach is representation alignment, where a strong vision foundation model is used to guide a 2D VLA model. However, existing methods usually apply supervision at only a single layer, failing to fully exploit the rich information distributed across depth; meanwhile, naïve multi-layer alignment can cause gradient interference. We introduce ROCKET, a residual-oriented multi-layer representation alignment framework that formulates multi-layer alignment as aligning one residual stream to another. Concretely, ROCKET employs a shared projector to align multiple layers of the VLA backbone with multiple layers of a powerful 3D vision foundation model via a layer-invariant mapping, which reduces gradient conflicts. We provide both theoretical justification and empirical analyses showing that a shared projector is sufficient and outperforms prior designs, and further propose a Matryoshka-style sparse activation scheme for the shared projector to balance multiple alignment losses. Our experiments show that, combined with a training-free layer selection strategy, ROCKET requires only about 4% of the compute budget while achieving 98.5% state-of-the-art success rate on LIBERO. We further demonstrate the superior performance of ROCKET across LIBERO-Plus and RoboTwin, as well as multiple VLA models. The code and model weights can be found at https://github.com/CASE-Lab-UMD/ROCKET-VLA.

cs.CV↗
arXiv2026

General sample size analysis for probabilities of causation: a delta method approach

Probabilities of causation (PoCs), such as the probability of necessity and sufficiency (PNS), are important tools for decision making but are generally not point identifiable. Existing work has derived bounds for these quantities using combinations of experimental and observational data. However, there is very limited research on sample size analysis, namely, how many experimental and observational samples are required to achieve a desired margin of error. In this paper, we propose a general sample size framework based on the delta method. Our approach applies to settings in which the target bounds of PoCs can be expressed as finite minima or maxima of linear combinations of experimental and observational probabilities. Through simulation studies, we demonstrate that the proposed sample size calculations lead to stable estimation of these bounds.

stat.ME↗
arXiv2026

Bounding Probabilities of Causation with Partial Causal Diagrams

Probabilities of causation are fundamental to individual-level explanation and decision making, yet they are inherently counterfactual and not point-identifiable from data in general. Existing bounds either disregard available covariates, require complete causal graphs, or rely on restrictive binary settings, limiting their practical use. In real-world applications, causal information is often partial but nontrivial. This paper proposes a general framework for bounding probabilities of causation using partial causal information. We show how the available structural or statistical information can be systematically incorporated as constraints in a optimization programming formulation, yielding tighter and formally valid bounds without full identifiability. This approach extends the applicability of probabilities of causation to realistic settings where causal knowledge is incomplete but informative.

cs.AI↗
arXiv2026

GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training

Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications is hindered by high latency, poor reproducibility, and unverifiable rewards relying on noisy visual proxies. To address the limitations, we present GUI-GENESIS, the first framework to automatically synthesize efficient GUI training environments with verifiable rewards. GUI-GENESIS reconstructs real-world applications into lightweight web environments using multimodal code models and equips them with code-native rewards, executable assertions that provide deterministic reward signals and eliminate visual estimation noise. Extensive experiments show that GUI-GENESIS reduces environment latency by 10 times and costs by over $28,000 per epoch compared to training on real applications. Notably, agents trained with GUI-GENESIS outperform the base model by 14.54% and even real-world RL baselines by 3.27% on held-out real-world tasks. Finally, we observe that models can synthesize environments they cannot yet solve, highlighting a pathway for self-improving agents.

cs.AI↗
arXiv2026

Bayesian Analyses of Proton Multiple Flow Components in Intermediate Heavy Ion Collisions with Momentum-Dependent Interactions

We perform a comprehensive Bayesian analyses of Au + Au collision data at 1.23 GeV/nucleon using an isospin-dependent Boltzmann-Uehling-Uhlenbeck transport model that incorporates a momentum-dependent mean field and medium-modified baryon-baryon cross sections. The model parameters are calibrated to empirical properties of nuclear matter at saturation density, with particular attention to variations in the incompressibility $K_0$. Within a Bayesian statistical framework and using a Gaussian Process emulator, we simultaneously extract constraints on the incompressibility $K_0$ and the in-medium baryon-baryon scattering modification factor $X$ by systematically comparing model predictions with HADES measurements of proton collective flow, including the slopes ($F_1$ and $F_3$) of directed and triangular flow, as well as elliptic ($v_2$) and quadrupole ($v_4$) flow observables. We find that the extracted incompressibility favors relatively small values, indicating a soft nuclear equation of state, while the inferred average $X$ values fall at $0.9$-$1.0$, suggesting mild suppression of baryon-baryon cross sections in the medium. Furthermore, we demonstrate that transport models employing momentum-independent mean fields require stiffer equations of state and stronger in-medium corrections to reproduce the same observables. These results highlight the critical role of momentum dependence in the mean field and its interplay with in-medium scattering in constraining the properties of dense nuclear matter from heavy-ion collisions.

nucl-th↗
arXiv2026

Learning Probabilities of Causation with Mask-Augmented Data

Probabilities of causation play a central role in modern decision making. Tian and Pearl first introduced formal definitions and derived tight bounds for three binary probabilities of causation, such as the probability of necessity and sufficiency (PNS). However, estimating these probabilities requires both experimental and observational distributions specific to each subpopulation, which are often unreliable or impractical to obtain from limited population-level data. To solve this problem, we propose two machine learning models: Exact-MLP and Mask-MLP, which are trained on a small set of reliable subpopulations and are able to predict PNS bounds for all other subpopulations. We validate our models across four Structural Causal Models (SCMs), each evaluated on population-level data with sample sizes between 100k and 200k. Our models achieve average mean absolute errors (MAEs) of roughly 0.03 on main tasks, reducing MAE by about 80% relative to the corresponding baselines. These results demonstrate both the feasibility of machine learning models for learning probabilities of causation and the effectiveness of the proposed approach.

stat.ML↗
arXiv2026

Fully Parallelized BP Decoding for Quantum LDPC Codes Can Outperform BP-OSD

This work presents a hardware-efficient and fully parallelizable decoder for quantum LDPC codes that leverages belief propagation (BP) with a speculative post-processing strategy inspired by classical Chase decoding algorithm. By monitoring bit-level oscillation patterns during BP, our method identifies unreliable bits and generates multiple candidate vectors to selectively flip syndromes. Each modified syndrome is then decoded independently using short-depth BP, a process we refer to as BP-SF (syndrome flip). This design eliminates the need for costly Gaussian elimination used in the current BP-OSD approaches. Our implementation achieves logical error rates comparable to or better than BP-OSD while offering significantly lower latency due to its high degree of parallelism for a variety of bivariate bicycle codes. Evaluation on the [[144,12,12]] bivariate bicycle code shows that the proposed decoder reduces average latency to approximately $70\%$ of BP-OSD. When post-processing is parallelized the average latency is reduced by $55\%$ compared to the single process implementation, with the maximum latency reaching as low as $18\%$. These advantages make it particularly well-suited for real-time and resource-constrained quantum error correction systems.

quant-ph↗
arXiv2026

QASMTrans: An End-to-End QASM Compilation Framework with Pulse Generation for Near-Term Quantum Devices

QASMTrans is a lightweight, high-performance, C++-based quantum compiler that bridges abstract quantum algorithms to device-level control and is designed for just-in-time (JIT) deployment on QPU testbeds with tightly integrated FPGAs or CPUs. We focus on achieving fast transpilation times on circuits of interest, we find more than 100x faster compilation than Qiskit in some circuits with similar circuit quality, enabling transpilation of large, high-depth circuits in seconds. Unlike existing tools, QASMTrans offers end-to-end device-pulse compilation and direct quantum control integration with QICK, closing the gap between logical circuits and hardware control enabling closed-loop optimization. QASMTrans supports latency-aware Application-tailored Gate Sets (AGS) at the pulse level, identifying high-impact gate sequences on the circuit critical path and synthesizing optimized pulse schedules using pre-defined robust circuit ansatz. Validated through integrated QuTiP pulse-level simulation, this is found to significantly reduce execution latency and can improve final-state fidelity by up to 12% in some tested circuits. QASMTrans further implements device-aware, noise-adaptive transpilation that uses device calibration data for circuit placement on high-quality qubits and can focus on the circuit critical path to reduce transpilation-pass time while maintaining comparable fidelity. Additionally, it introduces circuit space sharing via calibration-aware device partitioning, enabling concurrent execution of multiple circuits or shots on a single QPU. Moreover, QASMTrans is entirely self-contained and has no external library dependencies, making it easy for practical deployment. By combining fast compilation, pulse-level control, and noise-aware optimization, QASMTrans enables real-time adaptive algorithms such as ADAPT-VQE and ADAPT-QAOA.

quant-ph↗
arXiv2026

Scaling Agents for Computer Use

Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and leading to high variance in outcomes. While prior work has attempted to scale within a single rollout, such approaches have yielded limited gains. Scaling over multiple rollouts offers a more promising alternative but doing so effectively is challenging due to the difficulty of evaluating and selecting among long-horizon agent behaviors. We introduce Behavior Judge (BJudge), which addresses this challenge by representing agent executions as behavior narratives and comparing candidate behaviors at this level, substantially improving robustness and success rates. Using multiple rollouts, BJudge establishes a new state of the art (SoTA) in OSWorld at 72.6%, significantly outperforming prior methods and surpassing human-level performance at 72.36%, with comprehensive ablations validating key design choices. We further demonstrate strong generalization results to different operating systems on WindowsAgentArena and AndroidWorld. Crucially, our results highlight the strong effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and BJudge provides a practical framework to achieve this.

cs.AI↗
arXiv2026

Retrospective Feature Estimation for Continual Learning

The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches often retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored direction for CL called Retrospective Feature Estimation (RFE). RFE learns to reverse feature changes by aligning the features from the current trained DNN backward to the feature space of the old task, where performing predictions is easier. This retrospective process utilizes a chain of small feature mapping networks called retrospector modules. Empirical experiments on several CL benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods, motivating further research into retrospective mechanisms as a principled alternative for mitigating catastrophic forgetting in CL. Code is available at: https://github.com/mail-research/retrospective-feature-estimation.

cs.LG↗
arXiv2026

Towards Building Non-Fine-Tunable Foundation Models

Open-sourcing foundation models (FMs) enables broad reuse but also exposes model trainers to economic and safety risks from unrestricted downstream fine-tuning. We address this problem by building non-fine-tunable foundation models: models that remain broadly usable in their released form while yielding limited adaptation gains under task-agnostic unauthorized fine-tuning. We propose Private Mask Pre-Training (PMP), a pre-training framework that concentrates representation learning into a sparse subnetwork identified early in training. The binary mask defining this subnetwork is kept private, and only the final dense weights are released. This forces unauthorized fine-tuning without access to the mask to update parameters misaligned with pretraining subspace, inducing an intrinsic mismatch between the fine-tuning objective and the pre-training geometry. We provide theoretical analysis showing that this mismatch destabilizes gradient-based adaptation and bounds fine-tuning gains. Empirical results on large language models demonstrating that PMP preserves base model performance while consistently degrading unauthorized fine-tuning across a wide range of downstream tasks, with the strength of non-fine-tunability controlled by the mask ratio.

cs.LG↗
arXiv2026

FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards

Group Relative Policy Optimization (GRPO) has recently emerged as an effective approach for improving the reasoning capabilities of large language models through online multi-objective reinforcement learning. While personalization on private data is increasingly vital, traditional Reinforcement Learning (RL) alignment is often memory-prohibitive for on-device federated learning due to the overhead of maintaining a separate critic network. GRPO's critic-free architecture enables feasible on-device training, yet transitioning to a federated setting introduces systemic challenges: heterogeneous reward definitions, imbalanced multi-objective optimization, and high training costs. We propose FedMOA, a federated GRPO framework for multi-objective alignment under heterogeneous rewards. FedMOA stabilizes local training through an online adaptive weighting mechanism via hypergradient descent, which prioritizes primary reasoning as auxiliary objectives saturate. On the server side, it utilizes a task- and accuracy-aware aggregation strategy to prioritize high-quality updates. Experiments on mathematical reasoning and code generation benchmarks demonstrate that FedMOA consistently outperforms federated averaging, achieving accuracy gains of up to 2.2% while improving global performance, personalization, and multi-objective balance.

cs.LG↗
arXiv2026

Causal-Driven Feature Evaluation for Cross-Domain Image Classification

Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations, implicitly assuming that invariance implies reliability. However, features that are invariant across domains are not necessarily causally effective for prediction. In this work, we revisit OOD classification from a causal perspective and propose to evaluate learned representations based on their necessity and sufficiency under distribution shift. We introduce an explicit segment-level framework that directly measures causal effectiveness across domains, providing a more faithful criterion than invariance alone. Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance, particularly under challenging domain shifts, highlighting the value of causal evaluation for robust generalization.

cs.LG↗
arXiv2026

The Role of Quantum Computing in Advancing Scientific High-Performance Computing: A perspective from the ADAC Institute

Quantum computing (QC) has gained significant attention over the past two decades due to its potential for speeding up classically demanding tasks. This transition from an academic focus to a thriving commercial sector is reflected in substantial global investments. While advancements in qubit counts and functionalities continues at a rapid pace, current quantum systems still lack the scalability for practical applications, facing challenges such as too high error rates and limited coherence times. This perspective paper examines the relationship between QC and high-performance computing (HPC), highlighting their complementary roles in enhancing computational efficiency. It is widely acknowledged that even fully error-corrected QCs will not be suited for all computational task. Rather, future compute infrastructures are anticipated to employ quantum acceleration within hybrid systems that integrate HPC and QC. While QCs can enhance classical computing, traditional HPC remains essential for maximizing quantum acceleration. This integration is a priority for supercomputing centers and companies, sparking innovation to address the challenges of merging these technologies. The Accelerated Data Analytics and Computing Institute (ADAC) is comprised of globally leading HPC centers. ADAC has established a Quantum Computing Working Group to promote and catalyze collaboration among its members. This paper synthesizes insights from the QC Working Group, supplemented by findings from a member survey detailing ongoing projects and strategic directions. By outlining the current landscape and challenges of QC integration into HPC ecosystems, this work aims to provide HPC specialists with a deeper understanding of QC and its future implications for computationally intensive endeavors.

quant-ph↗