arXiv subjects

Yufei Zheng

Publications and source records attributed to Yufei Zheng.

10 recordsLinked to original sources

arXiv2026

Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence

Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural perception and fine-grained metric scale estimation. Existing multimodal large language models (MLLMs) typically address only one facet, ingesting either depth maps or point clouds as additional model inputs, which incurs substantial computational overhead and inherits the generalization limitations of upstream prediction models. We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence that takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone. Specifically, we introduce Metric-Structure Decoupled Queries (MSDQ) which employ two groups of learnable queries to respectively extract dense metric signals and sparse structural cues from the shared visual context, with a task-decoupled attention mask further preventing the two pathways from contaminating each other. Building on this, an Expert-Guided Visual Grounding (EVG) module projects the aggregated cues back to frame-level visual features and aligns them with vision foundation models, which serve purely as training-time supervision, rather than as model inputs. We further build a multi-task spatial instruction-tuning dataset (MTS) comprising 152{,}776 samples spanning 13 task types and three visual modalities, consolidated from six public datasets. Trained with a two-stage curriculum, GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.

cs.CV↗

arXiv2026

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive phenomenon: the performance of existing latent visual reasoning methods systematically degrades as the latent sequence grows longer. We reveal the root cause: Information Gain Collapse -- autoregressive generation makes each step highly dependent on prior outputs, so subsequent tokens can barely introduce new information. We further identify that heavily pooled ($\geq 128\times$) image embeddings used as supervision targets provide no more signal than meaningless placeholders. Motivated by these insights, we propose SCOLAR (Self-COnsistent LAtent Reasoning), which introduces a lightweight detransformer that leverages the LLM's full-sequence hidden states to generate auxiliary visual tokens in a single shot, with each token independently anchored to the original visual space. Combined with three-stage SFT and ALPO reinforcement learning, SCOLAR extends acceptable latent CoT length by over $30\times$, achieves state-of-the-art among open-source models on real-world reasoning benchmarks (+14.12% over backbone), and demonstrates strong out-of-distribution generalization.

cs.CV↗

arXiv2026

Quantum-enhanced Network Tomography

Network tomography refers to the use of inference techniques for inferring internal network states from end-to-end probes. Quantum probes, implemented by sending blocks of $n$ coherent-state pulses augmented with continuous-variable (CV) squeezing ($n=1$) or weak temporal-mode entanglement ($n>1$) over a lossy channel to a receiver with homodyne detection capabilities, are known to carry information about the channel transmissivity. Assuming a subset of nodes in an optical network is capable of sending and receiving such probes through intermediate nodes with all-optical switching capabilities, we leverage these quantum probes to estimate link transmissivities. To determine how to route the probes in a network, we propose a probe construction algorithm that guarantees link identifiability, while maximizing the number of information orthogonal sets of transmissivities. A set of probes induces a Fisher information matrix (FIM). We then derive two metrics, the determinant of the FIM and the trace of its inverse, to evaluate the performance of the probes. In particular, our results can be used to characterize the quantum improvement in estimating link transmissivities in a general optical network.

quant-ph↗

arXiv2026

StreamingClaw Technical Report

Emerging applications such as embodied intelligence, AI hardware, autonomous driving, and intelligent cockpits rely on a real-time perception-decision-action closed loop, posing stringent challenges for streaming video understanding. However, current agents mostly suffer from fragmented capabilities, such as supporting only offline video understanding, lacking long-term multimodal memory mechanisms, or struggling to achieve real-time reasoning and proactive interaction under streaming input. These shortcomings have become a key bottleneck for preventing agents from sustaining perception, making real-time decisions, and executing closed-loop actions in complex real-world environments, constraining their deployment and potential in dynamic, open physical worlds. To alleviate these issues, we propose StreamingClaw, a unified agent framework for streaming video understanding and embodied intelligence. Beyond maintaining full compatibility with the OpenClaw framework, it natively supports real-time, multimodal streaming interactions. StreamingClaw integrates five core capabilities: (1) It supports real-time streaming reasoning. (2) It supports reasoning about future events and proactive interaction under the online evolution of interaction objectives. (3) It supports multimodal long-term memory storage, hierarchical memory evolution, efficient memory retrieval, and memory sharing across multiple agents. (4) It supports a closed loop of perception-decision-action. In addition to conventional tools and skills, it also provides streaming tools and action-centric skills tailored for real-world physical environments. (5) It is compatible with the OpenClaw framework, allowing it to leverage the resources and support of the open-source community.

cs.CV↗

arXiv2025

MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm

We present MindGPT-4ov, a multimodal large language model (MLLM) that introduces a general post-training paradigm spanning data production, model training, and efficient deployment. It achieves state-of-the-art performance across multiple benchmarks at low cost, effectively enhancing the foundational capabilities of MLLMs and the generalization ability. Focusing on data construction, supervised fine-tuning strategies, and multimodal reinforcement learning methods, this work proposes three key innovations: (1) An information density-based data generation scheme, integrated with a dual-dimensional tree-structured label system, enabling automated generation of high-quality cross-domain data. (2) A collaborative curriculum supervised fine-tuning approach that balances the injection of domain-specific knowledge with the preservation of general capabilities. (3) A hybrid reinforcement learning paradigm that enhances reasoning ability while simultaneously addressing multi-objective optimization such as diversity exploration, maintenance of multimodal perception, and response conciseness. Moreover, we implement a series of infrastructure optimizations, such as 5D parallel training, operator optimization, and inference quantization to enhance training and inference efficiency while reducing the cost of domain adaptation. Experimental results demonstrate that the MindGPT-4ov model outperforms state-of-the-art models on benchmarks such as MMBench, MMStar, MathVision, and MathVista. In addition, MindGPT-4ov also demonstrates superior user experience in vertical domain tasks, enabling a seamless transition from academic research to industrial deployment. MindGPT-4ov provides a general post-training paradigm applicable to a wide range of MLLMs. The model weights, datasets, and code for the Qwen3-VL-based variants will be recently open-sourced to support the community's development of MLLMs.

cs.CV↗

arXiv2025

Do LLMs "Feel"? Emotion Circuits Discovery and Control

As the demand for emotional intelligence in large language models (LLMs) grows, a key challenge lies in understanding the internal mechanisms that give rise to emotional expression and in controlling emotions in generated text. This study addresses three core questions: (1) Do LLMs contain context-agnostic mechanisms shaping emotional expression? (2) What form do these mechanisms take? (3) Can they be harnessed for universal emotion control? We first construct a controlled dataset, SEV (Scenario-Event with Valence), to elicit comparable internal states across emotions. Subsequently, we extract context-agnostic emotion directions that reveal consistent, cross-context encoding of emotion (Q1). We identify neurons and attention heads that locally implement emotional computation through analytical decomposition and causal analysis, and validate their causal roles via ablation and enhancement interventions. Next, we quantify each sublayer's causal influence on the model's final emotion representation and integrate the identified local components into coherent global emotion circuits that drive emotional expression (Q2). Directly modulating these circuits achieves 99.65% emotion-expression accuracy on the test set, surpassing prompting- and steering-based methods (Q3). To our knowledge, this is the first systematic study to uncover and validate emotion circuits in LLMs, offering new insights into interpretability and controllable emotional intelligence.

cs.CL↗

arXiv2025

Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise

Prompt tuning has shown promising results, but its robustness and generalization to unseen categories remain limited. Through our experiments, we demonstrate that the complete removal of semantic noise is a key factor restricting robustness. Existing methods typically suppress or filter out semantic noise in the prompt space, inadvertently hindering the model's robustness and its ability to generalize to unseen categories. To address this, we propose ANPrompt, a robust prompt tuning framework that actively incorporates weak semantic noise. By clustering weakly perturbed features into noise prompts and integrating them with learnable tokens in both the text and vision encoders, ANPrompt ensures controlled exposure to semantic variations. To enhance the visual pathway, we introduce the Noise-Resistant Visual Prompt Prototype (NRVPP), which stabilizes visual semantics under weak perturbations. Additionally, we propose a Weak Alignment Loss (WALoss) at the logits level to enforce consistency between clean and perturbed predictions, providing stable supervision. By combining weak semantic noise exposure with logits-based consistency, ANPrompt prevents overfitting to specific phrasings while preserving semantic integrity. Extensive experiments across 11 benchmarks, including base-to-new splits, show that ANPrompt consistently outperforms existing prompt tuning methods, offering superior robustness to semantic noise and improved generalization across tasks.

cs.CV↗

arXiv2025

A Quantum Speedup in Localizing Transmission Loss Change in Optical Networks

The ability to localize transmission loss change to a subset of links in optical networks is crucial for maintaining network reliability, performance and security. \emph{Quantum probes}, implemented by sending blocks of $n$ coherent-state pulses augmented with continuous-variable (CV) squeezing ($n=1$) or weak temporal-mode entanglement ($n>1$) over a lossy channel to a receiver with homodyne detection capabilities, are known to be more sensitive than their quasi-classical counterparts in detecting a sudden increase in channel loss. The enhanced sensitivity can be characterized by the increased Kullback-Leibler (KL) divergence of the homodyne output, before and after the loss change occurs. When combined with the theory of quickest change detection (QCD), the increase in KL divergence translates into a decrease in detection latency. In this work, we first revisit quantum probes over a channel, generalizing previous results on $n=1$ (CV squeezed states) to arbitrary values of $n$. Assuming a subset of nodes in an optical network is capable of sending and receiving such probes through intermediate nodes with all-optical switching capabilities, we present a scheme for quickly detecting the links that have suffered a sudden drop in transmissivity. Since quantum probes lose their sensitivity with increasing loss in the channel, we first propose a probe construction algorithm that makes the set of links suffering transmission loss change identifiable, while minimizing the longest distance a probe traverses. We then introduce new cumulative sum (CUSUM) statistics with a stopping rule, which allows us to run the CUSUM algorithm to quickly localize the lossy links using our constructed probes. Finally, we show that the proposed scheme achieves a quantum speedup in decreasing the detection delay.

quant-ph↗

arXiv2025

Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation for Occluded Person Re-Identification

Occluded person re-identification aims to retrieve holistic images based on occluded ones. Existing methods often rely on aligning visible body parts, applying occlusion augmentation, or complementing missing semantics using holistic images. However, they face challenges in handling diverse occlusion scenarios not seen during training and the issue of feature contamination from holistic images. To address these limitations, we propose Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation (OGFR), which simultaneously mitigates these challenges. OGFR adopts a teacher-student distillation architecture that effectively incorporates diverse occlusion patterns into feature representation while transferring the purified discriminative holistic knowledge from the holistic to the occluded branch through reinforced knowledge distillation. Specifically, an Occlusion-Aware Vision Transformer is designed to leverage learnable occlusion pattern embeddings to explicitly model such diverse occlusion types, thereby guiding occlusion-aware robust feature representation. Moreover, we devise a Feature Erasing and Purification Module within the holistic branch, in which an agent is employed to identify low-quality patch tokens of holistic images that contain noisy negative information via deep reinforcement learning, and substitute these patch tokens with learnable embedding tokens to avoid feature contamination and further excavate identity-related discriminative clues. Afterward, with the assistance of knowledge distillation, the student branch effectively absorbs the purified holistic knowledge to precisely learn robust representation regardless of the interference of occlusions.

cs.CV↗

arXiv2023

Detecting TCP Packet Reordering in the Data Plane

Network administrators want to detect TCP-level packet reordering to diagnose performance problems and attacks. However, reordering is expensive to measure, because each packet must be processed relative to the TCP sequence number of its predecessor in the same flow. Due to the volume of traffic, detection should take place in the data plane as the packets fly by. However, restrictions on the memory size and the number of memory accesses per packet make it impossible to design an efficient algorithm for pinpointing flows with heavy packet reordering. In practice, packet reordering is typically a property of a network path, due to a congested or flaky link. Flows traversing the same path are correlated in their out-of-orderness, and aggregating out-of-order statistics at the IP prefix level provides useful diagnostic information. In this paper, we present efficient algorithms for identifying IP prefixes with heavy packet reordering under memory restrictions. First, we sample as many flows as possible, regardless of their sizes, but only for a short period at a time. Next, we separately monitor the large flows over long periods, in addition to the flow sampling. In both algorithms, we measure at the flow level, and aggregate statistics and allocate memory at the prefix level. Our simulation experiments, using packet traces from campus and backbone networks, and our P4 prototype show that our algorithms correctly identify $80\%$ of the prefixes with heavy packet reordering using moderate memory resources.

cs.NI↗