arXiv subjects

Teng Wang

Publications and source records attributed to Teng Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research.

cs.CV↗

arXiv2026

SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning

Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage preference learning to enhance the performance of vision-language models in fine-grained video captioning, while mitigating several limitations inherent to direct preference optimization (DPO). First, we propose a pipeline for constructing preference pairs that leverages the intrinsic properties of VLMs along with partial assistance from large language models, achieving an optimal balance between cost and data quality. Second, we propose Synergistic Preference Optimization (SynPO), a novel optimization method offering significant advantages over DPO and its variants. SynPO prevents negative preferences from dominating the optimization, explicitly preserves the model's language capability to avoid deviation of the optimization objective, and improves training efficiency by eliminating the need for the reference model. We extensively evaluate SynPO not only on video captioning benchmarks (e.g., VDC, VDD, VATEX) but also across well-established NLP tasks, including general language understanding and preference evaluation, using diverse pretrained models. Results demonstrate that SynPO consistently outperforms DPO variants while achieving 20\% improvement in training efficiency. Code is available at https://github.com/longmalongma/SynPO

cs.AI↗

arXiv2026

\textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation

Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly action-grounded visual dynamics modeling. Lacking awareness of how actions transform subsequent visual observations, agents cannot plan actions rationally, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a lightweight VLN framework that incorporates inverse dynamics supervision (IDS) as an explicit objective to embed action-grounded visual dynamics into policy learning. By jointly optimizing this visual dynamics with instruction-conditioned action prediction in a shared representation and action space, \textsc{NaVIDA} provides additional structured supervision that regularizes learning and leads to more stable and consistent navigation. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach.

cs.CV↗

arXiv2026

AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models

We present AutoTraces, an autoregressive vision-language-trajectory model for robot trajectory forecasting in humam-populated environments, which harnesses the inherent reasoning capabilities of large language models (LLMs) to model complex human behaviors. In contrast to prior works that rely solely on textual representations, our key innovation lies in a novel trajectory tokenization scheme, which represents waypoints with point tokens as categorical and positional markers while encoding waypoint numerical values as corresponding point embeddings, seamlessly integrated into the LLM's space through a lightweight encoder-decoder architecture. This design preserves the LLM's native autoregressive generation mechanism while extending it to physical coordinate spaces, facilitates modeling of long-term interactions in trajectory data. We further introduce an automated chain-of-thought (CoT) generation mechanism that leverages a multimodal LLM to infer spatio-temporal relationships from visual observations and trajectory data, eliminating reliance on manual annotation. Through a two-stage training strategy, our AutoTraces achieves SOTA forecasting accuracy, particularly in long-horizon prediction, while exhibiting strong cross-scene generalization and supporting flexible-length forecasting.

cs.CV↗

arXiv2026

AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos

Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating.

cs.CV↗

arXiv2026

Accelerating OpenPangu Inference on NPU via Speculative Decoding

To mitigate the Memory Wall bottleneck encountered by Large Language Models (LLMs) during inference on \textbf{NPU} hardware, and addressing the scarcity of native support for mainstream speculative decoding algorithms on domestic infrastructure, this study presents an end-to-end speculative inference acceleration scheme for OpenPangu-7B.

cs.DC↗

arXiv2026

Hermes: A Unified High-Performance NTT Architecture with Hybrid Dataflow

Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. Hybrid Homomorphic Encryption (HHE), which integrates arithmetic and logic FHE, further requires support for multiple NTT lengths. However, existing accelerators mainly optimize NTT throughput and do not provide unified support for HHE. This paper presents Hermes, a unified high-performance NTT architecture based on hybrid dataflow. Hermes exploits parallelism along both temporal and spatial dimensions and incorporates a fully pipelined on-chip computing core. A conflict-free on-chip fragmentation algorithm is introduced to resolve bank conflicts and enable burst HBM access, while an efficient dataflow improves computational intensity through data reuse, reducing bandwidth demand. Experimental results show that Hermes supports multiple NTT lengths and achieves up to 13.6x and 1.3x higher throughput than state-of-the-art GPU and FPGA accelerators, respectively. Our source code is available at https://anonymous.4open.science/r/Hermes_conf-4E6F.

cs.AR↗

arXiv2026

Reducing End-to-End Latency of Cause-Effect Chains with Shared Cache Analysis

Cause-effect chains, as a widely used modeling method in real-time embedded systems, are extensively applied in various safety-critical domains. End-to-end latency, as a key real-time attribute of cause-effect chains, is crucial in many applications. But the analysis of end-to-end latency for cause-effect chains on multicore platforms with shared caches still presents an unresolved issue. Traditional methods typically assume that the worst-case execution time (WCET) of each task in the cause-effect chain is known. However, in the absence of scheduling information, these methods often assume that all shared cache accesses result in misses, leading to an overestimation of WCET and, consequently, affecting the accuracy of end-to-end latency. However, effectively integrating scheduling information into the WCET analysis process of the chains may introduce two challenges: first, how to leverage the structural characteristics of the chains to optimize shared cache analysis, and second, how to improve analysis accuracy while avoiding state space explosion. To address these issues, this paper proposes a novel end-to-end latency analysis framework designed for multi-chain systems on multicore platforms with shared caches. This framework extracts scheduling information and structural characteristics of cause-effect chains, constructing fine-grained and scalable inter-core memory access contexts at the basic block level for time-sensitive shared cache analysis. This results in more accurate WCET (TSC-WCET) estimates, which are then used to derive the end-to-end latency. Finally, we conduct experiments on dual-core and quad-core systems with various cache configurations, which show that under certain settings, the average maximum end-to-end latency of cause-effect chains is reduced by up to 34% and 26%.

eess.SY↗

arXiv2026

A Timing-Anomaly Free Dynamic Scheduling on Heterogeneous Systems

Heterogeneous systems commonly adopt dynamic scheduling algorithms to improve resource utilization and enhance scheduling flexibility. However, such flexibility may introduce timing anomalies, wherein locally reduced execution times can lead to an increase in the overall system execution time. This phenomenon significantly complicates the analysis of Worst-Case Response Time (WCRT), rendering conventional analysis either overly pessimistic or unsafe, and often necessitating exhaustive state-space exploration to ensure correctness. To address this challenge, this paper presents the first timing-anomaly-free dynamic scheduling algorithm for heterogeneous systems, referred to as Deterministic Dynamic Execution. It achieves a safe and tight WCRT estimate through a single offline simulation execution. The core idea is to apply deterministic execution constraints, which partially restrict the resource allocation and execution order of tasks at runtime. Based on a formally defined execution progress model for heterogeneous system scheduling, we prove the correctness of the proposed execution constraints and their ability to eliminate timing anomalies. Furthermore, we propose two methods to generate execution constraints. The first method derives execution constraints directly from the execution traces produced by existing scheduling algorithms. The second method is a heuristic-based approach that constructs execution constraints, enabling further reduction of the WCRT. Experimental results on synthetically generated DAG task sets under various system configurations demonstrate that, compared to traditional dynamic scheduling algorithms, our approach not only eliminates timing anomalies but also effectively reduces both the WCRT and response time jitter.

eess.SY↗

arXiv2026

CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern recognition research. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first diagnostic benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to analyze and integrate spatiotemporal patterns from dynamic visual streams. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 63.5% accuracy on causal reasoning tasks, compared to the 91.3% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLMs architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for advancing pattern recognition methodologies in multi-video scenarios, providing architectural insights for next-generation models. The data and evaluation code are available at: https://github.com/Hokhim2/CVBench.

cs.CV↗

arXiv2026

Charge-dependent nucleon-nucleon interaction at N$^3$LO in nuclear lattice effective field theory

The nuclear lattice effective field theory (NLEFT) is an efficient tool for solving nuclear many-body problems, which takes high-fidelity lattice chiral interactions as input and computes nuclear low-energy observables via quantum Monte Carlo techniques. In this work, we present the first next-to-next-to-next-to-leading order (N$^3$LO) chiral forces on the lattice with the isospin-breaking effects fully taken into account. We focus on both the charge-independence breaking (CIB) and charge-symmetry breaking (CSB) effects. Specifically, we include the isospin-breaking effect from the mass difference between the charged and neutral pions in the one-pion-exchange potential (OPEP), the Coulomb force for the $pp$ interaction and the contribution of two additional charge-dependent contact operators. We also explicitly incorporate the two-pion-exchange potentials which was mostly neglected in previous NLEFT calculations. With these improvements, we are able to accurately reproduce the $np$ and $pp$ scattering phase shifts up to relative momentum $p \sim 200$ MeV as well as the deuteron properties. The construction of these charge-dependent lattice nuclear forces establishes a solid foundation for future high-precision nuclear ab initio calculations within the NLEFT framework.

nucl-th↗

arXiv2026

Investigating nuclear beta decay using lattice quantum Monte Carlo approach

We present an \textit{ab initio} calculation of nuclear $β$ decay within the framework of nuclear lattice effective field theory (NLEFT), employing auxiliary-field quantum Monte Carlo methods to solve the nuclear many-body problem. Our approach combines next-to-next-to-leading order two- and three-body chiral interactions with one- and two-body axial current operators, all consistently derived in chiral effective field theory. Low-energy constants are determined exclusively from nucleon-nucleon scattering phase shifts and few-body observables for systems with $A \leq 3$. Using these interactions and transition operators, we perform two-channel Monte Carlo simulations to compute the $β$-decay matrix element for $^6$He, obtaining results in reasonable agreement with experimental measurements. To address the Monte Carlo sign problem, we implement a perturbative expansion around a leading-order Hamiltonian with approximate Wigner-SU(4) symmetry. This systematic approach provides a foundation for extending NLEFT simulations to precision studies of weak processes in medium-mass nuclei.

nucl-th↗

arXiv2025

Fully analogue in-memory neural computing via quantum tunneling effect

Fully analogue neural computation requires hardware that can implement both linear and nonlinear transformations without digital assistance. While analogue in-memory computing efficiently realizes matrix-vector multiplication, the absence of learnable analogue nonlinearities remains a central bottleneck. Here we introduce KANalogue, a fully analogue realization of Kolmogorov-Arnold Networks (KANs) that instantiates univariate basis functions directly using negative-differential-resistance (NDR) devices. By mapping the intrinsic current-voltage characteristics of NDR devices to learnable coordinate-wise nonlinear functions, KANalogue embeds function approximation into device physics while preserving a fully analogue signal path. Using cold-metal tunnel diodes as a representative platform, we construct diverse nonlinear bases and combine them through crossbar-based analogue summation. Experiments on MNIST, FashionMNIST, and CIFAR-10 demonstrate that KANalogue achieves competitive accuracy with substantially fewer parameters and higher crossbar node efficiency than analogue MLPs, while approaching the performance of digital KANs under strict hardware constraints. The framework is not limited to a specific device technology and naturally generalizes to a broad class of NDR devices. These results establish a device-grounded route toward scalable, energy-efficient, fully analogue neural networks.

cs.ET↗

arXiv2025

Epitome: Pioneering an Experimental Platform for AI-Social Science Integration

Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an open experimental platform that operationalizes this paradigm through Matrix-like social worlds where researchers can study isolated human subjects and groups interacting with LLM agents. This maintains ecological validity while enabling precise manipulation of social dynamics. Epitome approaches three frontiers: (1) methodological innovation using LLM confederates to reduce complexity while scaling interactions; (2) empirical investigation of human behavior in AI-saturated environments; and (3) exploration of emergent properties in hybrid collectives. Drawing on interdisciplinary foundations from management, communication, sociology, psychology, and ethics, the platform's modular architecture spans foundation model deployment through data collection. We validate Epitome through replication of three seminal experiments, demonstrating capacity to generate robust findings while reducing experimental complexity. This tool provides crucial insights for understanding how humans navigate AI-mediated social realities, knowledge essential for policy, education, and human-centered AI design.

cs.CY↗

arXiv2025

ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge

Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hin dered by high inference latency. While smooth robotic interaction requires control frequencies of 20 to 30 Hz, current VLA models typi cally operate at only 3-5 Hz on edge devices due to the memory bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge plat forms. At the core of ActionFlow is a Cross-Request Pipelin ing strategy, a novel scheduler that redefines VLA inference as a macro-pipeline of micro-requests. The strategy intelligently batches memory-bound Decode phases with compute-bound Prefill phases across continuous time steps to maximize hardware utilization. Furthermore, to support this scheduling, we propose a Cross Request State Packed Forward operator and a Unified KV Ring Buffer, which fuse fragmented memory operations into efficient dense computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dy namic manipulation on edge hardware. Our work is available at https://anonymous.4open.science/r/ActionFlow-1D47.

cs.AI↗

arXiv2025

R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios

Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video scenarios, failing to reflect the complex and diverse nature of real-world audio-visual events in videos. To bridge this gap, we firstly introduce R-AVST, a dataset for audio-visual reasoning featuring fine-grained spatio-temporal annotations. In constructing this, we design a pipeline consisting of LLM-based key object extraction, automatic spatial annotation and manual quality inspection, resulting in over 5K untrimmed videos with 27K objects across 100 types of audio-visual events. Building on this dataset, we define three core tasks for spatio-temporal reasoning in audio-visual scenes and generate more than 8K high-quality, evenly distributed question-answer pairs to effectively benchmark model performance. To further enhance reasoning, we propose AVST-Zero, a reinforcement learning-based model that avoids intermediate supervision, directly optimizing behavior via carefully designed multi-dimensional rewards. Extensive experiments validate the effectiveness of our R-AVST in advancing audio-visual spatio-temporal reasoning, upon which AVST-Zero demonstrates competitive performance compared to existing models. To the best of our knowledge, R-AVST is the first dataset designed for real-world audio-visual spatio-temporal reasoning, and AVST-Zero offers a novel perspective for tackling future challenges in this domain.

cs.CV↗

arXiv2025

Video Understanding with Large Language Models: A Survey

With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding that harness the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (general, temporal, and spatiotemporal) reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into three main types: Video Analyzer x LLM, Video Embedder x LLM, and (Analyzer + Embedder) x LLM. Furthermore, we identify five sub-types based on the functions of LLMs in Vid-LLMs: LLM as Summarizer, LLM as Manager, LLM as Text Decoder, LLM as Regressor, and LLM as Hidden Layer. Furthermore, this survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at https://github.com/yunlong10/Awesome-LLMs-for-Video-Understanding.

cs.CV↗

arXiv2025

UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-specialize on individual tasks, neglecting the equal importance of these different events for a complete understanding of video content. In this work, we aim to develop a unified framework to solve TAL, SED and AVEL tasks together to facilitate holistic video understanding. However, it is challenging since different tasks emphasize distinct event characteristics and there are substantial disparities in existing task-specific datasets (size/domain/duration). It leads to unsatisfactory results when applying a naive multi-task strategy. To tackle the problem, we introduce UniAV, a Unified Audio-Visual perception network to effectively learn and share mutually beneficial knowledge across tasks and modalities. Concretely, we propose a unified audio-visual encoder to derive generic representations from multiple temporal scales for videos from all tasks. Meanwhile, task-specific experts are designed to capture the unique knowledge specific to each task. Besides, instead of using separate prediction heads, we develop a novel unified language-aware classifier by utilizing semantic-aligned task prompts, enabling our model to flexibly localize various instances across tasks with an impressive open-set ability to localize novel categories. Extensive experiments demonstrate that UniAV, with its unified architecture, significantly outperforms both single-task models and the naive multi-task baseline across all three tasks. It achieves superior or on-par performances compared to the state-of-the-art task-specific methods on ActivityNet 1.3, DESED and UnAV-100 benchmarks.

cs.CV↗