arXiv subjects

Xianglong Wang

Publications and source records attributed to Xianglong Wang.

10 recordsLinked to original sources

arXiv2026

Training-Free Inference Acceleration for Video Large Language Models: Methods, Trade-offs, and Evaluation

Video Large Language Models (VLMs) have demonstrated strong capabilities in video understanding and reasoning, but processing long visual sequences incurs substantial computational, latency, and memory overhead. This survey examines training-free inference acceleration, focusing on reducing inference costs while preserving task-relevant spatiotemporal evidence. We organize existing methods by their intervention stages in the inference pipeline, covering input, visual encoding, projector, prefill, and decoding. Post-training quantization (PTQ) is discussed separately as a cross-stage extension with varying calibration requirements. We analyze how intervention position affects evidence preservation and computational savings, and why local efficiency improvements may not translate into end-to-end acceleration. We complement this analysis with quantitative evidence from prior studies and our own experiments under a shared evaluation setting to assess accuracy-latency trade-offs.

cs.CV↗

arXiv2026

OpenHome: From Perception to Insight in Smart-Home Camera Videos

Vision language models (VLMs) have been increasingly adopted in consumer smart-home camera systems to interpret recorded videos and provide insights. However, video clips captured from smart-home cameras are different from curated web videos dominating existing VLM benchmarks. Smart-home video clips often do not contain subtitles or narration and are captured from different viewing angles, under various lighting conditions, and in diverse scenarios. However, the capabilities of the model in this domain, under sparse visual signals and limited context, are not fully assessed by existing VLM benchmarks. To close this gap, we introduce OpenHome, a visual-only, four-option multiple-choice benchmark for evaluating smart-home video understanding. It contains 2,254 questions on 1,118 real-world video clips and organizes 10 tasks into three capability levels. Perception evaluates visible content, Reasoning evaluates causal, spatial, and temporal relationships, and Insight evaluates subject intent, supporting evidence and appropriate homeowner responses. Based on the dataset, we describe the task design, data pipeline and evaluation protocol, and report results for 32 closed-source and open-weight VLMs. The best model, Gemini 4 Argon, reaches 81.2% overall accuracy. Frontier closed-source models outperform open-weight models on every level. The best closed-source model leads the best open-weight model by 16.3% on Perception, 22.4% on Reasoning and 37.4% on Insight.

cs.CV↗

arXiv2026

TTS-Q: Speaker-Aware Post-Training Quantization of Text-to-Speech Diffusion Transformers

Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size and multi-step sampling put them out of reach of the on-device, assistive, and real-time applications that need them most. Post-training quantization (PTQ) shrinks such models without retraining, but it has been built for language and vision, not speech. At 4 bits, a strong quantizer leaves intelligibility close to full precision but consistently erodes speaker timbre, so error rates stay low while the voice drifts from the target speaker. We ask why quantization hurts speech, where the damage lives, and whether it can be repaired without retraining. To find out, we run the first 4-bit weight-and-activation (W4A4) PTQ study of a TTS diffusion transformer at 1B and 3.5B. The timbre cost comes from both the weight and the activation quantization, but only the activation part has the timestep structure a precision schedule can exploit. We therefore introduce TTS-Q, which selects hard-to-quantize items from task-matched calibration candidates and applies a budget-balanced mixed-precision schedule that assigns higher precision to late-step feed-forward activations. TTS-Q recovers timbre best at both scales, at no cost to intelligibility. Separately, the deployed calibrated-W4A4 reference reduces peak memory on GPU, providing a practical reference for resource-constrained TTS deployment.

cs.SD↗

arXiv2026

TeQCo: Temporal Quota Consistency for Training-Free Video Token Compression

Video token compression must control both temporal coverage and task relevance, but sequential stages can conflict: a content-driven allocation stage may be overwritten by a global ranking that removes entire temporal positions. We identify this as an allocation conflict and propose TeQCo, a training-free framework that resolves it through temporal quota consistency. TeQCo allocates candidate capacity from first-order changes in normalized frame representations and aggregates all tokens within each frame into a compact candidate set. Candidates are then scored by prior-corrected task attention and selected within integer frame quotas inherited from the first-stage counts. Content variation determines temporal capacity; question relevance determines which candidates fill it. This design guarantees an exact token budget and a per-frame coverage floor whenever feasible. On the 2,700-question Video-MME benchmark with Qwen3-VL-8B, TeQCo achieves 68.52% accuracy at 510 ms TTFT, a 32.9% TTFT reduction with a 1.00-percentage-point accuracy decrease.

eess.IV↗

arXiv2026

ContextTom: Training-Free Video VLM Acceleration with Early Spatial Context

Video vision-language models process thousands of visual tokens before producing an answer. Reducing these tokens early saves computation, but also determines which evidence reaches the language model. We introduce ContextTom, a training-free framework that separates the timing of temporal and spatial compression. Its central idea is to compress time before vision encoding while preserving spatial coverage through early multimodal processing. A fixed-budget temporal partition produces representative medoid anchors, supplemented with bounded local detail from neighboring observations. The anchors retain their complete spatial grids through a short decoder prefix, allowing question tokens to access the visual evidence and completing Qwen3-VL's multi-level visual injections. ContextTom then selects spatial representatives using query attention and agreement across visual feature levels, and continues directly from their computed states. This schedule reduces vision computation and later decoder workload while reusing the prefix. On Qwen3-VL-8B, ContextTom achieves 76.22% accuracy on Video-MME Short with a mean time-to-first-token (TTFT) of 123.5 ms, yielding a 2.77x speedup over full-input inference. It matches the full-input accuracy of 72.20% on EgoSchema with a 2.82x speedup and achieves a 5.54x speedup on LongVideoBench at 59.24% accuracy.

eess.IV↗

arXiv2026

Decision-Oriented Uncertainty Quantification for Risk Control in Earth System Spatiotemporal Foundation Models

Earth system modeling is shifting from task-specific predictors toward foundation models with general spatiotemporal representation capabilities. Although these models can jointly encode dynamic Earth fields, external forcings, and static geographic context for multistep forecasting, accurate point predictions or statistically calibrated intervals alone are insufficient for high-impact applications such as extremeweather warning, flood control, renewable-energy dispatch, and emergency resource allocation. What matters in practice is whether predictive uncertainty can be translated into reliable decision risk under specific actions, loss functions, and risk preferences. We propose a decision-oriented uncertainty quantification framework for Earth system spatiotemporal foundation models. The framework produces predictive distributions of future states and uses a decision risk adapter to map forecast samples, decision context, and utility functions into action-conditional risks. A utility-aware calibration module further enforces reliability at the downstream decision-loss level rather than only at the forecast-value level. Calibrated risks are then used to select warning, dispatch, inspection, or resource-allocation actions. Compared with the strongest baseline, the proposed method reduces decision regret by 18.7%, lowers the missed-event rate from 14.2% to 9.1%, and improves expected utility by 11.6%, while maintaining 90.4% predictive coverage and reducing decision calibration error from 0.083 to 0.047. These results suggest that decision-oriented uncertainty quantification can improve the robustness and operational value of Earth system foundation models in risk-sensitive applications.

cs.LG↗

arXiv2026

MedTRACE: Tool-Augmented Multimodal Clinical Reasoning Agents for Evidence-Grounded Decision-Making

Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiological signals. Existing models typically map these inputs directly to diagnoses without explicitly assessing evidence sufficiency, tool-use requirements, or diagnostic uncertainty. This paper presents MedTRACE, a tool-augmented multimodal clinical reasoning agent for evidence-grounded decision-making. MedTRACE uses modality-specific encoders to construct a unified patient-state representation and performs an iterative loop of hypothesis formation, toolaware deliberation, and evidence verification. It dynamically invokes visual grounding, evidence retrieval, and structured parsing tools to locate diagnosis-relevant regions, retrieve clinical knowledge and similar cases, and extract structured findings. The acquired evidence enters an evidence memory, where a consistency verifier confirms or revises the current hypothesis. MedTRACE outputs a diagnosis together with supporting evidence, an auditable reasoning trace, and calibrated confidence. Experiments on multiple multimodal clinical diagnosis benchmarks show that MedTRACE improves diagnostic accuracy by 5.4% and AUROC by 4.7 percentage points over the strongest baseline. It also improves evidenceselection F1 by 8.2 percentage points and visual-grounding IoU by 6.5 percentage points, reduces expected calibration error by 31.6%, and decreases unsupported diagnostic errors by 27.8%. These results demonstrate that active evidence acquisition and verification improve the accuracy, interpretability, and reliability of multimodal clinical decisionmaking.

cs.CL↗

arXiv2026

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models that excel at SER are too costly for edge devices. Multi-teacher knowledge distillation can compress them into a lightweight student, but two challenges remain: teacher reliability varies across batches, and logit-level distillation ignores inter-sample relational structure. We propose Adaptive Multi-teacher Relational Distillation (AMRD) to address both. A one-class SVM on each teacher's logit similarity matrix assigns per-batch weights favoring more coherent teachers. A relational distillation loss aligns teacher and student similarity matrices, capturing structure that logit matching misses. On IEMOCAP and CREMA-D datasets across four student architectures, AMRD outperforms single-teacher distillation baselines in most settings, and ablations confirm both components yield complementary gains.

cs.LG↗

arXiv2024

OpenAirLink: Reproducible Wireless Channel Emulation using Software Defined Radios

This paper presents OpenAirLink(OAL), an open-source channel emulator for reproducible testing of wireless scenarios. OAL is implemented on off-the-shelf software-defined radios (SDR) and presents a smaller-scale alternative to expensive commercially available channel emulators. Path loss and propagation delay are the fundamental aspects of emulating a wireless channel. OAL provides a simple method to change these aspects in real-time. The emulator is implemented using a finite impulse response (FIR) filter. The FIR filter is written in Verilog and flashed on the SDRs Field Programmable Gate Array (FPGA). Most processing transpires on the FPGA, so OAL does not require high-performance computing hardware and SDRs. We validate the performance of OAL and demonstrate the utility of such a channel emulation tool using two examples. We believe that open-source channel emulators such as OAL can make reproducible wireless experiments accessible to many researchers in the scientific community.

cs.NI↗

arXiv2023

Ordered and Binary Speaker Embedding

Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dimensions of the embedding vector via a nested dropout and converts the sorted vectors to binary codes via Bernoulli sampling. The resultant ordered binary codes offer some important merits such as hierarchical clustering, reduced memory usage, and fast retrieval. These merits were empirically verified by comprehensive experiments on a speaker identification task with the VoxCeleb and CN-Celeb datasets.

cs.SD↗