arXiv subjects

Kai Lu

Publications and source records attributed to Kai Lu.

At least 19 recordsLinked to original sources

arXiv2026

MARS: Multi-stage Accelerated Read Stack for Large-buffer Buffered Reads

Large-buffer reads increasingly connect data-intensive applications to high-speed storage. They amortize system-call overhead and create a larger in-kernel window for organizing page-cache work and submitting I/O. However, Linux buffered read primarily exploits only the former benefit. Within a large read, its conventional interleaved path repeatedly switches among fine-grained page-cache operations, amplifying metadata and serial orchestration overheads and failing to consistently expose enough in-flight requests to modern parallel SSDs. We present MARS, a multi-stage accelerated read stack for synchronous large-buffer buffered reads. MARS treats each large-range read as one unit of work and stages page-cache operations by data structure and dependency. During I/O waits, it handles user-buffer page faults and performs reorderable data copies early. Opportunistic kernel workers then copy remaining data in parallel and, when the backend provides sufficient parallelism, optionally submit I/O in parallel. We implement MARS in Linux 6.6.58. For MiB-scale fio reads, MARS improves bandwidth by up to 6.56 times over Linux. On five NVMe SSDs in RAID0, it reaches 36.87 GiB/s for 128 MiB random reads, 4.44 times Linux. MARS also accelerates DuckDB/Parquet queries by 1.80--2.15 times and ExecuTorch model loading by 3.17--3.61 times.

cs.OS↗

arXiv2026

CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation

Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing. However, traditional Image Change Captioning (ICC) methods lack spatial grounding, limiting their precision. We introduce Image Change Captioning and Segmentation (ICCS), a new multimodal task that jointly requires structured change description and pixel-level localization. To address ICCS, we propose the Change-aware Captioning and Reasoning Chain (CCRC), a dual-chain framework that decouples semantic reasoning from spatial segmentation. The first chain, Chain-of-Change-Captioning (CCC), enhances fine-grained change perception via a visual fusion module based on Multi-Head Change-aware Attention inserted between the visual and language components of a Multimodal Large Language Model (MLLM). CCC also determines whether a change is segmentable. If not, it alone generates the caption. Otherwise, the second chain, Chain-of-Change-Segmenting (CCS), is activated, leveraging spatial priors from CCC and refining masks with a Change-aware Token Refiner for accurate boundary localization. We evaluate CCRC on both synthetic and real-world change detection benchmarks with pixel-level supervision. Experiments show CCRC achieves state-of-the-art performance.

cs.CV↗

arXiv2026

Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

Baichuan-M4 is Baichuan Intelligence's clinical-grade medical large model, designed for continuous care rather than single-turn medical question answering. It is built as a coordinated medical agent system around three pillars: Baichuan-Harness, a unified runtime that keeps reinforcement-learning training and real-world deployment consistent while enforcing action constraints, tool use, long-term patient memory, and multi-agent coordination; a core reasoning model trained with a continuous-care reinforcement-learning framework that integrates span-level reward modeling (SPAR++), reasoning-path compression, curriculum learning, and stabilized policy optimization; and a clinical tool layer for patient-memory management, authoritative evidence-based retrieval, and multimodal medical perception across documents, X-rays, and dermatology. On a cross-dimensional medical evaluation suite, Baichuan-M4 attains leading results in static medical knowledge and safety, dynamic OSCE-style consultation, long-context clinical memory, evidence-based retrieval, medical document OCR, and multimodal image understanding, while lowering the hallucination rate to 3.3%.

cs.AI↗

arXiv2026

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in VLMs based on token granularity, which is time-consuming in the search process and hardware inefficient during computation. This paper introduces a novel approach called WindowQuant, which employs window-adaptive mixed-precision quantization to optimize the KV cache. WindowQuant consists of two modules: window-level quantization search and window-level KV cache computation. Window-level quantization search quickly determines the optimal bit-width configuration of the KV cache windows based on the similarity scores between the corresponding visual token windows and the text prompt, maintaining the model accuracy. Furthermore, window-level KV cache computation reorders the KV cache windows before quantization, avoiding the hardware inefficiency caused by mixed-precision quantization in inference computation. Extensive experiments demonstrate that WindowQuant outperforms state-of-the-art VLM models and KV cache quantization methods on various datasets.

cs.CV↗

arXiv2026

ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference

Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM, these approaches either demand frequent GPU-CPU data transfers or impose extensive CPU computation requirements, resulting in poor GPU utilization as the system waits for I/O operations or CPU processing to complete. We propose ScoutAttention, a novel KV cache offloading framework that accelerates LLM inference through collaborative GPU-CPU attention computation. To prevent CPU computation from bottlenecking the system, ScoutAttention introduces GPU-CPU collaborative block-wise sparse attention that significantly reduces CPU load. Unlike conventional parallel computing approaches, our framework features a novel layer-ahead CPU pre-computation algorithm, enabling the CPU to initiate attention computation one layer in advance, complemented by asynchronous periodic recall mechanisms to maintain minimal CPU compute load. Experimental results demonstrate that ScoutAttention maintains accuracy within 2.4% of baseline while achieving 2.1x speedup compared to existing offloading methods.

cs.LG↗

arXiv2026

CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding

Current work on robot failure detection and correction typically operates in a post hoc manner, analyzing errors and applying corrections only after failures occur. This work introduces CycleVLA, a system that equips Vision-Language-Action models (VLAs) with proactive self-correction, the capability to anticipate incipient failures and recover before they fully manifest during execution. CycleVLA achieves this by integrating a progress-aware VLA that flags critical subtask transition points where failures most frequently occur, a VLM-based failure predictor and planner that triggers subtask backtracking upon predicted failure, and a test-time scaling strategy based on Minimum Bayes Risk (MBR) decoding to improve retry success after backtracking. Extensive experiments on the LIBERO and LIBERO-Plus simulation benchmarks show that CycleVLA surpasses the state-of-the-art VLA {\pi}0.5, improves success rates by correcting execution failures across VLAs of varying capability, from under-trained ones to fully converged policies, and that MBR serves as an effective zero-shot test-time scaling strategy for VLAs. On a real robot, CycleVLA reaches a 91% average success rate on one precise and two long-horizon manipulation tasks. We further conduct stress tests with multiple manually injected perturbations (e.g., swapping in a distractor at the expected location while relocating the true target object mid-execution), where CycleVLA corrects ~80% of injected failures and maintains success rates comparable to unperturbed execution. Project Page: https://dannymcy.github.io/cyclevla/

cs.RO↗

arXiv2025

COOPERA: Continual Open-Ended Human-Robot Assistance

To understand and collaborate with humans, robots must account for individual human traits, habits, and activities over time. However, most robotic assistants lack these abilities, as they primarily focus on predefined tasks in structured environments and lack a human model to learn from. This work introduces COOPERA, a novel framework for COntinual, OPen-Ended human-Robot Assistance, where simulated humans, driven by psychological traits and long-term intentions, interact with robots in complex environments. By integrating continuous human feedback, our framework, for the first time, enables the study of long-term, open-ended human-robot collaboration (HRC) in different collaborative tasks across various time-scales. Within COOPERA, we introduce a benchmark and an approach to personalize the robot's collaborative actions by learning human traits and context-dependent intents. Experiments validate the extent to which our simulated humans reflect realistic human behaviors and demonstrate the value of inferring and personalizing to human intents for open-ended and long-term HRC. Project Page: https://dannymcy.github.io/coopera/

cs.RO↗

arXiv2025

Baichuan-M2: Scaling Medical Capability with Large Verifier System

As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.

cs.LG↗

arXiv2025

DCPO: Dynamic Clipping Policy Optimization

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This problem arises primarily due to fixed clipping bounds for token-level probability ratios and the standardization of identical rewards, which can lead to ineffective gradient updates and underutilization of generated responses. In this work, we propose Dynamic Clipping Policy Optimization(DCPO), which introduces a dynamic clipping strategy that adaptively adjusts clipping bounds based on token-specific prior probabilities to enhance token-level exploration, and a smooth advantage standardization technique that standardizes rewards across cumulative training steps to improve the response-level effective utilization of generated responses. DCPO achieved state-of-the-art performance on four benchmarks based on four different models. In particular, DCPO achieved an Avg@1 of 46.7 under greedy decoding and an Avg@32 of 38.8 under 32 times sampling on the AIME24 benchmark, surpassing DAPO (36.7/31.6), GRPO (36.7/32.1) and GSPO (40.0/34.9) on the Qwen2.5-Math-7B model. On the AIME25 benchmark based on Qwen2.5-14B, DCPO achieves a performance of (23.3/19.0), surpassing GRPO (13.3/10.5), DAPO (20.0/15.3) and GSPO (16.7/9.9). Furthermore, DCPO achieved an average 28% improvement in the nonzero advantage over GRPO in four models, doubled the training efficiency over DAPO, and significantly reduced the token clipping ratio by an order of magnitude compared to both GRPO and DAPO, while achieving superior performance. These results highlight DCPO's effectiveness in leveraging generated data more efficiently for reinforcement learning in large language models.

cs.CL↗

arXiv2025

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity and variability of natural language: essentially equivalent problems often appear in diverse surface forms, often obscured by redundant or distracting details. This imposes a dual burden on SLMs: they must first extract the core problem from complex linguistic input, and then perform reasoning based on that understanding. The resulting vast and noisy problem space hinders optimization, particularly for models with limited capacity. To address this, we propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space-a semantically simplified yet expressive domain. This enables SLMs to focus on reasoning over standardized inputs, free from linguistic variability. Within this framework, we introduce DURIT (Decoupled Understanding from Reasoning via Iterative Training), a three-step algorithm that iteratively: (1) mapping natural language problems via reinforcement learning, (2) aligns reasoning trajectories through self-distillation, and (3) trains reasoning policies in the problem space. The mapper and reasoner are co-trained in an alternating loop throughout this process. Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks. Beyond improving reasoning capabilities, DURIT also improves the robustness of reasoning, validating decoupling understanding from reasoning as an effective strategy for strengthening SLMs.

cs.CL↗

arXiv2025

DeepGo: Predictive Directed Greybox Fuzzing

The state-of-the-art DGF techniques redefine and optimize the fitness metric to reach the target sites precisely and quickly. However, optimizations for fitness metrics are mainly based on heuristic algorithms, which usually rely on historical execution information and lack foresight on paths that have not been exercised yet. Thus, those hard-to-execute paths with complex constraints would hinder DGF from reaching the targets, making DGF less efficient. In this paper, we propose DeepGo, a predictive directed grey-box fuzzer that can combine historical and predicted information to steer DGF to reach the target site via an optimal path. We first propose the path transition model, which models DGF as a process of reaching the target site through specific path transition sequences. The new seed generated by mutation would cause the path transition, and the path corresponding to the high-reward path transition sequence indicates a high likelihood of reaching the target site through it. Then, to predict the path transitions and the corresponding rewards, we use deep neural networks to construct a Virtual Ensemble Environment (VEE), which gradually imitates the path transition model and predicts the rewards of path transitions that have not been taken yet. To determine the optimal path, we develop a Reinforcement Learning for Fuzzing (RLF) model to generate the transition sequences with the highest sequence rewards. The RLF model can combine historical and predicted path transitions to generate the optimal path transition sequences, along with the policy to guide the mutation strategy of fuzzing. Finally, to exercise the high-reward path transition sequence, we propose the concept of an action group, which comprehensively optimizes the critical steps of fuzzing to realize the optimal path to reach the target efficiently.

cs.SE↗

arXiv2025

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization methods cannot take both effectiveness and efficiency into account. In this paper, we propose MoQAE, a novel mixed-precision quantization method via mixture of quantization-aware experts. First, we view different quantization bit-width configurations as experts and use the traditional mixture of experts (MoE) method to select the optimal configuration. To avoid the inefficiency caused by inputting tokens one by one into the router in the traditional MoE method, we input the tokens into the router chunk by chunk. Second, we design a lightweight router-only fine-tuning process to train MoQAE with a comprehensive loss to learn the trade-off between model accuracy and memory usage. Finally, we introduce a routing freezing (RF) and a routing sharing (RS) mechanism to further reduce the inference overhead. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art KV cache quantization approaches in both efficiency and effectiveness.

cs.CV↗

arXiv2025

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models

Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and exploration failures remain inevitable. A critical but underexplored direction is the timely termination of exploration to overcome these challenges. We observe a diminishing marginal effect between exploration steps and exploration rates and analyze the cost-benefit relationship of exploration. Inspired by this, we propose RATE-Nav, a Region-Aware Termination-Enhanced method. It includes a geometric predictive region segmentation algorithm and region-Based exploration estimation algorithm for exploration rate calculation. By leveraging the visual question answering capabilities of visual language models (VLMs) and exploration rates enables efficient termination.RATE-Nav achieves a success rate of 67.8% and an SPL of 31.3% on the HM3D dataset. And on the more challenging MP3D dataset, RATE-Nav shows approximately 10% improvement over previous zero-shot methods.

cs.CV↗

arXiv2025

BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation

Since the point cloud data is inherently irregular and unstructured, point cloud semantic segmentation has always been a challenging task. The graph-based method attempts to model the irregular point cloud by representing it as a graph; however, this approach incurs substantial computational cost due to the necessity of constructing a graph for every point within a large-scale point cloud. In this paper, we observe that boundary points possess more intricate spatial structural information and develop a novel graph attention network known as the Boundary-Aware Graph attention Network (BAGNet). On one hand, BAGNet contains a boundary-aware graph attention layer (BAGLayer), which employs edge vertex fusion and attention coefficients to capture features of boundary points, reducing the computation time. On the other hand, BAGNet employs a lightweight attention pooling layer to extract the global feature of the point cloud to maintain model accuracy. Extensive experiments on standard datasets demonstrate that BAGNet outperforms state-of-the-art methods in point cloud semantic segmentation with higher accuracy and less inference time.

cs.CV↗

arXiv2025

MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs

When applying pre-trained large language models (LLMs) to address anomaly detection tasks, the multivariate time series (MTS) modality of anomaly detection does not align with the text modality of LLMs. Existing methods simply transform the MTS data into multiple univariate time series sequences, which can cause many problems. This paper introduces MADLLM, a novel multivariate anomaly detection method via pre-trained LLMs. We design a new triple encoding technique to align the MTS modality with the text modality of LLMs. Specifically, this technique integrates the traditional patch embedding method with two novel embedding approaches: Skip Embedding, which alters the order of patch processing in traditional methods to help LLMs retain knowledge of previous features, and Feature Embedding, which leverages contrastive learning to allow the model to better understand the correlations between different features. Experimental results demonstrate that our method outperforms state-of-the-art methods in various public anomaly detection datasets.

cs.CL↗

arXiv2025

RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations

Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despite previous progress that estimates OOD uncertainty based on the detection model and in-distribution (ID) samples, we explore using pre-trained vision-language representations for object-level OOD detection. We first discuss the limitations of applying image-level CLIP-based OOD detection methods to object-level scenarios. Building upon these insights, we propose RUNA, a novel framework that leverages a dual encoder architecture to capture rich contextual information and employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively. We introduce a few-shot fine-tuning approach that aligns region-level semantic representations to further improve the model's capability to discriminate between similar objects. Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection, particularly in challenging scenarios with diverse and complex object instances.

cs.CV↗

arXiv2025

Error-mitigated entanglement-assisted quantum process tomography

In the era of noisy intermediate-scale quantum computing, it is of crucial importance to verify quantum processes and extract information. Quantum process tomography is a typical approach, however, both resource-intensive and vulnerable to state preparation and measurement errors. Here, we propose an error-mitigated entanglement-assisted quantum process tomography (EM-EAPT) framework to address these limitations. By leveraging a maximally entangled state to reduce state preparation complexity and integrating error mitigation techniques, our method significantly enhances robustness against SPAM errors. Experimental validation on a superconducting processor demonstrates the efficacy of EM-EAPT for two-qubit and three-qubit quantum processes. Results show more accurate average gate fidelities close to the realistic estimation, achieving 98.1$\pm$ 0.03% for a CNOT gate and 88.1%$\pm$ 0.04% for a cascaded CNOT process after error mitigation, compared to non-mitigated implementations. This work advances practical quantum verification tools for NISQ devices, enabling higher-fidelity characterization of quantum processes under realistic noise conditions.

quant-ph↗

arXiv2025

Telegraph flux noise induced beating Ramsey fringe in transmon qubits

Ramsey oscillations typically exhibit an exponential decay envelope due to environmental noise. However, recent experiments have observed nonmonotonic Ramsey fringes characterized by beating patterns, which deviate from the standard behavior. These beating patterns have primarily been attributed to charge-noise fluctuations. In this paper, we investigate the flux-noise origin of these nonmonotonic Ramsey fringes in frequency-tunable transmon qubits. We develop a random telegraph noise (RTN) model to simulate the impact of telegraph-like flux-noise sources on Ramsey oscillations. Our simulations demonstrate that strong flux-RTN sources can induce beating patterns in the Ramsey fringes, showing excellent agreement with experimental observations in transmon qubits influenced by electronic environment-induced flux-noise. Our findings provide valuable insights into the role of flux-noise in qubit decoherence and underscore the importance of considering flux-noise RTN when analyzing nonmonotonic Ramsey fringes.

quant-ph↗