arXiv subjects

Qirui Wang

Publications and source records attributed to Qirui Wang.

At least 19 recordsLinked to original sources

arXiv2026

SpikingMOT: A Spike-Driven Multi-Object Tracker

Multi-object tracking (MOT) plays a fundamental role in visual perception, where accurate trajectory prediction is essential for reliable target association under complex motion patterns. Recent trackers have improved motion modeling with densely activated artificial neural networks, yet they largely overlook whether such dense responses are necessary for trajectory prediction. In this paper, we formulate activation sparsity preference (ASP) by tackling two key questions: 1. How can we identify a model architecture that appropriately and formally explains ASP, and 2. How can we translate this explanation into competitive tracking performance. Theoretical analysis shows that sparse gating is no worse than state-independent dropout under the same activation rate. Based on this insight, SpikingMOT is proposed as a spike-driven tracker that adaptively models sparse trajectory dynamics with spiking neural networks (SNNs). Specifically, SpikingMOT decomposes each trajectory state into pseudo-trajectory bases and uses the current prediction error to calibrate the posterior for next-frame prediction. With this brain-inspired loop, SpikingMOT achieves state-of-the-art performance in extensive experiments, 74.9 HOTA on SportsMOT and 56.5 HOTA on DanceTrack, while reducing the parameters and energy by 72% and 86.7%, respectively. These results bring SNNs into MOT, opening a promising direction for efficient tracking.

cs.NE↗

arXiv2026

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning

Large reasoning models often solve problems through long chain-of-thought (CoT) traces, yet much of this computation is spent on redundant derivations, repeated self-verification, and detours that do not improve the final answer. Existing on-policy self-distillation methods reduce this cost by matching a student model to a concise copy of itself on prefixes sampled from the student's own rollouts. We show that this objective has an initialization bottleneck. Since supervision is applied only to visited prefixes, training from a verbose base model places the KL loss on contexts that are often noisy, redundant, or already off track. In such regions, a concise teacher can provide only local corrections, while the student continues to explore trajectories that an efficient reasoner should avoid. In this paper, we propose BIRD(Bootstrapped Iterative Self-Reasoning Distillation), a two-stage self-reasoning distillation method that improves the rollout distribution before on-policy training. BIRD first samples concise solutions from the base model under a brevity instruction, keeps only answer-correct traces, and performs a lightweight prompt-switch SFT step. The traces are generated with the brevity instruction but learned under the original task prompt, turning instruction-induced conciseness into a default reasoning behavior. Starting from this warm model, BIRD then applies on-policy reverse-KL distillation with a concise self-teacher, now on cleaner and more informative prefixes. Across Qwen3 series models, BIRD achieves a stronger accuracy-efficiency trade-off than prompting and cold-start on-policy distillation on MATH-500 and AIME benchmarks. On Qwen3-8B, it improves MATH-500 accuracy from 86.2% to 92.0% while reducing the average response length from 3,099 to 1,115 tokens. These results highlight prefix support as a central factor in efficient reasoning distillation.

cs.CL↗

arXiv2026

Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension

Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page OCR to multi-page memory QA. Yet existing VTC pipelines treat rendering and layout as a fixed, content-agnostic preprocessing step and offer little mechanistic understanding of how VLMs internally process visualized text. Through a focused empirical study on VTC QA tasks, we reveal that VLMs exhibit a localization-without-utilization regime: evidence-localizing attention emerges sharply in the middle-to-late layers and is largely decoupled from answer correctness, yet simply enlarging the localized spans on the rendered page recovers a large fraction of the failures. Building on these observations, we propose AGAR (Attention-Guided Adaptive Rendering), a training-free, model-agnostic method that leverages a VLM's own middle-to-late layer attention to identify the top-K important visual patches, maps them back to word spans, and re-renders the page with those spans enlarged before re-inferring the answer. Extensive experiments across nine VTC benchmarks (short-form, long-context, and multi-page memory QA) and four VLM backbones show that AGAR (i)consistently improves off-the-shelf VLMs as a plug-and-play enhancement, (ii)composes with VLM post-training to yield further gains, and (iii)remains robust under both visual- and text-side input degradation.

cs.CV↗

arXiv2026

Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances

Functional affordance grounding requires more than recognizing an object: an agent must localize the specific region that supports an interaction, such as the handle to pull or the button to press. This is difficult for training-free vision-language pipelines because actionable regions are often small, visually ambiguous, and repeated across multiple same-category instances in a scene. We propose AFFORDMEM, a framework that grounds 3D functional affordances by remembering geometry at two levels. The first is cross-scene affordance memory: the agent maintains a category-level memory bank of RGB images with affordance regions rendered as overlays, and recalls the most informative examples at query time to guide a frozen VLM toward small operable subregions that text-only prompting consistently misses. The second is in-scene spatial memory: as the agent processes the scene, it organizes candidate instances and their 3D spatial relations into a structured scene graph, enabling the language model to resolve references over distant or currently unobserved candidates such as "the second handle from the top." AFFORDMEM requires no model fine-tuning and no target-scene annotation, using a reusable memory bank built from source scenes. On SceneFun3D, our method improves AP50 over the prior training-free state of the art by 3.23 on Split 0 and 3.7 on Split 1. Ablation studies support complementary benefits: cross-scene affordance memory improves fine-grained localization, while in-scene spatial memory provides the larger gain on spatially qualified queries. The project homepage is available at the project page.

cs.CV↗

arXiv2026

CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning

Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-structured tables. However, while methods like Chain-of-Thought (CoT) introduce reasoning chains, purely symbolic methodes are inherently limited by their blindness to holistic visual patterns. To address this, we propose the Coarse-to-Fine Multimodal Synthesis framework (CFMS), a novel two-stage paradigm that hierarchically decouples high-level visual perception from granular symbolic reasoning. In the Coarse Stage, CFMS leverages the Multimodal Large Language Models (MLLMs) to perform a one-time synthesis of a multi-perspective knowledge tuple. This tuple subsequently serves as a dynamic reasoning map to guide the fine stage, where a symbolic engine executes a targeted and efficient sequence of iterative operations over the table. Extensive experiments on the WikiTQ and TabFact benchmarks demonstrate that CFMS achieves competitive accuracy. The framework exhibits particular robustness when handling large tables and when instantiated with smaller backbone models, validating its effectiveness and generalizability.

cs.AI↗

arXiv2026

Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval

Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic focus and event correlations. We present KDC-Net, a Knowledge-Refined Dual Context-Aware Network that tackles these issues from both textual and visual perspectives. On the text side, a Hierarchical Semantic Aggregation module captures and adaptively fuses multi-scale phrase cues to enrich query semantics. On the video side, a Dynamic Temporal Attention mechanism employs relative positional encoding and adaptive temporal windows to highlight key events with local temporal coherence. Additionally, a dynamic CLIP-based distillation strategy, enhanced with temporal-continuity-aware refinement, ensures segment-aware and objective-aligned knowledge transfer. Experiments on PRVR benchmarks show that KDC-Net consistently outperforms state-of-the-art methods, especially under low moment-to-video ratios.

cs.CV↗

arXiv2026

PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning

Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable breakthroughs in large language models by incentivizing reasoning capabilities through strategic reward design, their potential remains largely unexplored in the 3D perception domain. This naturally raises a pivotal question: Can RL-based methods effectively empower 3D point cloud fine-tuning? In this paper, we propose PointRFT, the first reinforcement fine-tuning paradigm tailored specifically for point cloud representation learning. We select three prevalent 3D foundation models and devise specialized accuracy reward and dispersion reward functions to stabilize training and mitigate distribution shifts. Through comprehensive few-shot classification experiments comparing distinct training paradigms, we demonstrate that PointRFT consistently outperforms vanilla supervised fine-tuning (SFT) across diverse benchmarks. Furthermore, when organically integrated into a hybrid Pretraining-SFT-RFT paradigm, the representational capacity of point cloud foundation models is substantially unleashed, achieving state-of-the-art performance particularly under data-scarce scenarios.

cs.CV↗

arXiv2026

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity.

cs.AI↗

arXiv2026

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict computation and memory budgets. In practice, lightweight systems for object detection, instance segmentation, and pose estimation are still dominated by CNN-based architectures such as YOLO, while compact Vision Transformers (ViTs) often struggle to achieve comparable accuracy-efficiency trade-offs, even with large-scale pretraining. We argue that this gap arises primarily from insufficient task-specific representation learning in small-scale ViTs, rather than from an inherent mismatch between ViTs and edge dense prediction. To address this issue, we introduce EdgeCrafter, a unified compact ViT framework for edge dense prediction centered on ECDet, a detection model built on a distilled compact backbone and an edge-friendly encoder-decoder design. The resulting detection-distilled representation transfers directly to instance segmentation and human pose estimation through lightweight task-specific prediction modules. Without using task annotations beyond COCO, ECDet-S achieves 51.7 box AP with fewer than 10M parameters, while ECInsSeg-X and ECPose-X reach 48.4 mask AP and 74.8 keypoint AP, respectively. As a complementary but more compute-intensive setting, Objects365 detection pretraining consistently improves performance across all scales, with the X variants reaching 59.9 box AP, 49.8 mask AP, and 75.9 keypoint AP. These results show that compact ViTs, when combined with task-specialized distillation and edge-aware design, can be a practical and competitive solution for edge dense prediction. Code is available at: https://intellindust-ai-lab.github.io/projects/EdgeCrafter

cs.CV↗

arXiv2026

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.

cs.CL↗

arXiv2025

MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images

Spatial reasoning (SR), the ability to infer 3D spatial information from 2D inputs, is essential for real-world applications such as embodied AI and autonomous driving. However, existing research primarily focuses on indoor environments and typically relies on multi-view observations, which limits their generalizability to outdoor scenarios and constrains their applicability to monocular images, the most common real-world setting. In this work, we propose MonoSR, a large-scale monocular spatial reasoning dataset that spans diverse scenarios including indoor, outdoor, and object-centric settings, and supports multiple question types. MonoSR provides a path toward open-world monocular spatial reasoning. Beyond introducing the dataset, we evaluate advanced vision-language models to reveal their limitations on this challenging task. We further analyze whether auxiliary information is crucial for monocular spatial reasoning and offer practical guidance for designing future models. These contributions collectively establish a foundation for advancing monocular spatial reasoning in real-world, open-world environments.

cs.CV↗

arXiv2025

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving robustness. In this context, we propose a new black-box attack method that leverages the interpretability of large models. We introduce the Sparse Feature Perturbation Framework (SFPF), a novel approach for adversarial text generation that utilizes sparse autoencoders to identify and manipulate critical features in text. After using the SAE model to reconstruct hidden layer representations, we perform feature clustering on the successfully attacked texts to identify features with higher activations. These highly activated features are then perturbed to generate new adversarial texts. This selective perturbation preserves the malicious intent while amplifying safety signals, thereby increasing their potential to evade existing defenses. Our method enables a new red-teaming strategy that balances adversarial effectiveness with safety alignment. Experimental results demonstrate that adversarial texts generated by SFPF can bypass state-of-the-art defense mechanisms, revealing persistent vulnerabilities in current NLP systems.However, the method's effectiveness varies across prompts and layers, and its generalizability to other architectures and larger models remains to be validated.

cs.CL↗

arXiv2025

Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models

Full-duplex spoken dialogue systems promise to transform human-machine interaction from a rigid, turn-based protocol into a fluid, natural conversation. However, the central challenge to realizing this vision, managing overlapping speech, remains critically under-evaluated. We introduce Full-Duplex-Bench v1.5, the first fully automated benchmark designed to systematically probe how models behave during speech overlap. The benchmark simulates four representative overlap scenarios: user interruption, user backchannel, talking to others, and background speech. Our framework, compatible with open-source and commercial API-based models, provides a comprehensive suite of metrics analyzing categorical dialogue behaviors, stop and response latency, and prosodic adaptation. Benchmarking five state-of-the-art agents reveals two divergent strategies: a responsive approach prioritizing rapid response to user input, and a floor-holding approach that preserves conversational flow by filtering overlapping events. Our open-source framework enables practitioners to accelerate the development of robust full-duplex systems by providing the tools for reproducible evaluation.

eess.AS↗

arXiv2025

Spatial Speech Translation: Translating Across Space With Binaural Hearables

Imagine being in a crowded space where people speak a different language and having hearables that transform the auditory space into your native language, while preserving the spatial cues for all speakers. We introduce spatial speech translation, a novel concept for hearables that translate speakers in the wearer's environment, while maintaining the direction and unique voice characteristics of each speaker in the binaural output. To achieve this, we tackle several technical challenges spanning blind source separation, localization, real-time expressive translation, and binaural rendering to preserve the speaker directions in the translated audio, while achieving real-time inference on the Apple M2 silicon. Our proof-of-concept evaluation with a prototype binaural headset shows that, unlike existing models, which fail in the presence of interference, we achieve a BLEU score of up to 22.01 when translating between languages, despite strong interference from other speakers in the environment. User studies further confirm the system's effectiveness in spatially rendering the translated speech in previously unseen real-world reverberant environments. Taking a step back, this work marks the first step towards integrating spatial perception into speech translation.

cs.CL↗

arXiv2025

SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements

Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing. This enables improved detection accuracy and more efficient hardware designs by bypassing the ISP. However, RAW object detection is challenging due to limited training data, unbalanced pixel distributions, and sensor noise. To address this, we propose SimROD, a lightweight and effective approach for RAW object detection. We introduce a Global Gamma Enhancement (GGE) module, which applies a learnable global gamma transformation with only four parameters, improving feature representation while keeping the model efficient. Additionally, we leverage the green channel's richer signal to enhance local details, aligning with the human eye's sensitivity and Bayer filter design. Extensive experiments on multiple RAW object detection datasets and detectors demonstrate that SimROD outperforms state-of-the-art methods like RAW-Adapter and DIAP while maintaining efficiency. Our work highlights the potential of RAW data for real-world object detection. Code is available at https://ocean146.github.io/SimROD2025/.

cs.CV↗

arXiv2025

Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.

cs.CL↗

arXiv2025

Multi-Modal Video Feature Extraction for Popularity Prediction

This work aims to predict the popularity of short videos using the videos themselves and their related features. Popularity is measured by four key engagement metrics: view count, like count, comment count, and share count. This study employs video classification models with different architectures and training methods as backbone networks to extract video modality features. Meanwhile, the cleaned video captions are incorporated into a carefully designed prompt framework, along with the video, as input for video-to-text generation models, which generate detailed text-based video content understanding. These texts are then encoded into vectors using a pre-trained BERT model. Based on the six sets of vectors mentioned above, a neural network is trained for each of the four prediction metrics. Moreover, the study conducts data mining and feature engineering based on the video and tabular data, constructing practical features such as the total frequency of hashtag appearances, the total frequency of mention appearances, video duration, frame count, frame rate, and total time online. Multiple machine learning models are trained, and the most stable model, XGBoost, is selected. Finally, the predictions from the neural network and XGBoost models are averaged to obtain the final result.

cs.CV↗

arXiv2024

A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation

Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and low-frequency nature of neural codecs introduced a new way to generate speech with token-based models. As these tokens encode information at various levels of granularity, from coarse to fine, most existing works focus on how to better generate the coarse tokens. In this paper, we focus on an equally important but often overlooked question: How can we better resynthesize the waveform from coarse tokens? We point out that both the choice of learning target and resynthesis approach have a dramatic impact on the generated audio quality. Specifically, we study two different strategies based on token prediction and regression, and introduce a new method based on Schr\"odinger Bridge. We examine how different design choices affect machine and human perception.

eess.AS↗