arXiv subjects

Bin Ma

Publications and source records attributed to Bin Ma.

At least 19 recordsLinked to original sources

arXiv2026

Rest-frame Ultraviolet Variability of Quasars in the Cosmic Himalayas Overdensity

Some high-redshift overdensities show an enhanced incidence of AGNs, suggesting that large-scale environment may influence supermassive black hole fuelling and triggering. Whether environment also affects AGN variability remains unclear. Using the Cosmic Himalayas (CH), an extreme concentration of 11 type 1 quasars at z=2.16-2.20, we investigate possible offsets in rest-frame ultraviolet variability relative to quasars with comparable redshifts, black hole masses, and Eddington ratios. We construct a parent sample of 1,138 Stripe 82 quasars at 2.11<=z<=2.25 and combine photometry from the SDSS, the PS1, and the ZTF to build observer-frame g- and r-band light curves spanning up to 27~yr. We compare DRW parameters and ensemble structure functions (SFs) with control pseudo-samples matched in black hole mass and Eddington ratio, and use injection--recovery simulations to forecast the detectability of a CH-like offset. The CH quasars show a tendency toward shorter DRW damping timescales (median offsets of -0.32 and -0.13 dex in g and r) and slightly higher asymptotic amplitudes. None of the four DRW comparisons is statistically significant, including the largest offset in the g-band damping timescale (p=0.16). Ensemble SFs generally exceed matched-control medians, although 18 of 19 lag bins per band remain within the 95% pointwise envelopes. Assuming a true uniform -0.32 dex g-band timescale offset, injection--recovery simulations predict an 80% probability of nominal 3sigma detection with approximately 60 quasars of comparable variability scatter and data quality. If confirmed, the tentative variability offsets may suggest that large-scale environment influences accretion-flow variability beyond its potential role in quasar triggering. Larger samples with higher-precision light curves, such as those expected from the LSST, are required to test this possibility.

astro-ph.GA↗

arXiv2026

A Multi-Engine Dataflow for MoE Decoding on AWS Tranium

Mixture-of-Experts (MoE) decoding on scratchpad-based tensor accelerators (STA) is dominated by moving expert weights while the compute engines sit idle. This traffic is hard to hide, because the experts are known only after routing, and hard to shrink without losing quality or adding critical-path work. We present CARDAN, which represents each expert-weight matrix as a vector-quantized component plus a shared-basis low-rank component and co-designs this representation with a multi-engine decoding dataflow. The representation separates expert-common from expert-private work, so the dataflow overlaps DMA with computation on several engines. Across five MoE families on AWS Trainium3, CARDAN matches or improves BF16-teacher perplexity across all five models and speeds up batch-one decoding by 1.15-1.31x over AWS dense MoE megakernels, rising to 1.7x at batch size 16.

cs.AR↗

arXiv2026

DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium

On AWS Trainium2, every component of a diffusion model runs as a program compiled ahead of time for fixed shapes, while pipelines differ across models, prompt lengths across requests, and caching decisions across denoising steps. We present Difflet, a serving engine in which five model pipelines share one compilation backend, joint attention is split across cores by attention head, and a host controller decides at each denoising step whether to run the denoiser or reuse its earlier output. A small probe program computes the caching signal on the device and returns one number per step, and a resident model process keeps every program loaded across requests. Across five image and video model families, fused attention accelerates denoiser steps by 1.2-4.3x over the same framework using PyTorch/XLA attention, and at 32.8k visual tokens it is the only attention that compiles. On four of the five models, resident serving is 1.5-3.4x faster than standalone runs that reload weights from a warm file cache for each generation.

cs.DC↗

arXiv2026

Qwen-Audio-3.1-ASR Technical Report

We present Qwen-Audio-3.1-ASR, a family of audio-language models that builds upon its predecesor Qwen-Audio-3.0-ASR with improved speech recognition and expanded capabilities in speaker-diarized transcription and general audio understanding. The family retains support for 30 languages and 16 Chinese dialects, together with instruction-controlled capabilities including historical-context conditioning, hierarchical hotword customization, and native transcription polishing. Speaker-diarized ASR produces structured outputs containing speaker labels, timestamps, and recognized text, maintaining consistent speaker labels across turns and the representation of overlapping speech. The general audio understanding capabilities cover audio-, speech-, and music-captioning, temporal grounding and sound event detection, as well as audio question answering and multiple-choice reasoning. These tasks broaden the application scope from recognizing spoken words to interpreting speakers, acoustic events, and their temporal relations. To accommodate different deployment requirements, the family includes variants for asynchronous file transcription, low-latency streaming, interactive voice input, and non-streaming recognition, with speaker-diarized transcription and general audio understanding available in certain variants. Evaluations span conventional ASR, multilingual and dialectal speech, speaker-diarized transcription, and general audio understanding, demonstrating the capabilities of the Qwen-Audio-3.1-ASR family across transcription and broader audio analysis tasks.

cs.SD↗

arXiv2026

ZenFlow: Enabling Stall-Free Offloading for LLM Training

Fine-tuning large language models (LLMs) often exceeds GPU memory limits, prompting systems to offload model states to CPU memory. However, existing offloaded training frameworks like ZeRO-Offload treat all parameters equally and update the full model on the CPU, causing severe GPU stalls, where fast, expensive GPUs sit idle, waiting for slow CPU updates and limited-bandwidth PCIe transfers. We present ZenFlow, a new offloaded training framework that decouples updates between GPU and CPU by prioritizing important gradients. ZenFlow performs in-place updates of important gradients on GPU while offloading and accumulating less important ones on CPU without blocking training iterations, fully overlapping CPU work with GPU computation. To make this importance-aware design scalable, ZenFlow leverages a novel spatio-temporal locality of important gradients, concentrated in specific positions that remain stable across iterations, to make important gradient identification efficient and lightweight while preserving fidelity. Evaluation shows that ZenFlow achieves up to 5x end-to-end speedup, 2x lower PCIe traffic, 85% less GPU stalls, and up to 72% lower cloud GPU cost, all while preserving accuracy.

cs.DC↗

arXiv2026

TierBPF: Page Migration Admission Control for Tiered Memory via eBPF

Software-based memory tiering systems decide which pages to place on the slower or faster tier. However, they do not consider two important factors that greatly influence application performance: the size of the migrated pages, and the underlying hardware device and tiering topology. We introduce TierBPF, a software mechanism that can be plugged into existing memory tiering systems to take these factors into account, by making architecture-aware page admission decisions. TierBPF is implemented as a set of eBPF hooks, allowing users to define their custom policies. In order to make its decisions, TierBPF utilizes a lightweight tracking mechanism for page profiling which is not dependent on the application's working set size. TierBPF, integrated into three memory tiering systems and evaluated with 17 workloads, achieves geomean throughput gains of up to 15.9% with improvements of up to 75% for individual workloads.

cs.OS↗

arXiv2026

An Efficient and Effective Watermarking Scheme for the Protection of the Intellectual Property Rights of Video Generative Models

The rapid development of video generative models (VGMs) has enabled the generation of highly realistic synthetic videos, raising concerns about the intellectual property rights (IPR) of these models. In particular, two closely related forensic tasks remain largely unaddressed: synthetic video verification (determining whether a video was generated by a protected VGM) and model ownership verification (determining whether a suspect VGM is an unauthorized copy of a protected VGM). In this paper, we propose a new in-generation watermarking scheme that can address the two verification tasks. First, a novel video watermarking network named VidMark is presented, which incorporates a two-scale discrete wavelet transform (DWT) decomposition and a global temporal attention block (GTAB) to enhance watermark robustness and imperceptibility. Second, we present a decoder-guided fine-tuning procedure. By leveraging the frozen VidMark decoder, this process enables VGMs to synthesize videos carrying an imperceptible, robust, and model-specific watermark. Finally, two verification frameworks are established to perform synthetic video verification and model ownership verification. Extensive experiments on representative VGMs demonstrate that the proposed scheme achieves over 99% watermark extraction accuracy and 100% verification accuracy on both tasks, with negligible impact on video generation quality. Furthermore, the watermarks exhibit strong robustness against a comprehensive range of video-level and model-level attacks.

cs.CV↗

arXiv2026

Style as Cover: Deep Image Steganography via Stylized Transmission

Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradigm becomes vulnerable once the original cover is exposed or can be reliably approximated. In this paper, we propose StyleStegaNet, a stylized image hiding framework that replaces cover matching with style-concealment transmission. Instead of transmitting a cover-like stego image, StyleStegaNet generates stylized stego images conditioned on publicly available style references, redefining steganography invisibility from cover-preserving concealment to behavior-level camouflage based on style transformation. Such a setting poses a substantial challenge to reliable secret recovery, since neural stylization can significantly alter the feature statistics exploited by deep hiding methods. To address this challenge, StyleStegaNet decouples the overall task into four coordinated stages: stego generation, stylized transmission, structure-preserving reconstruction, and secret recovery. Moreover, StyleStegaNet is optimized with a progressive three-stage training strategy, in which wavelet-domain constraints and perceptual supervision guide the recoverable information toward structural representations. We further provide an analysis showing that secret recoverability is largely restricted to the normalized structural subspace, offering a mechanistic explanation for why directly stylized baselines fail and why a reconstruction-guided recovery path is necessary. Extensive experiments on DIV2K and MS-COCO datasets demonstrate the effectiveness of StyleStegaNet. And few-shot image steganalysis with two deep detectors further shows detection accuracy near random guessing, approximately 51\%.

cs.CV↗

arXiv2026

Disentangle and Drop: Robust Universal Removal of Image Watermarks via Reconstructive Grayscale Residual Decomposition

Invisible image watermarks are commonly evaluated against benign postprocessing operations such as compression, resizing, blur, and color changes. These tests leave out a different threat: a learned remover that preserves semantic image content while discarding residual evidence that carries the payload. We propose Disentangle and Drop (DnD), an attack that is agnostic to the watermark method and treats watermark removal as a representation routing problem. DnD decomposes a watermarked image into a semantic grayscale carrier and an auxiliary residual branch, and then suppresses the residual branch to reduce watermark evidence. The model is trained with latent spectral perturbations and low-strength diffusion exposure so that the drop operation remains stable under adaptive reconstruction. Experiments on seven representative watermark families show that one shared operating setting gives competitive removal with high visual fidelity. Operating scans and ablations separate usable attacks from image-damaging settings: stronger noise or diffusion can raise removal scores by damaging the image, while the practical regime comes from dropping the residual latent. These results argue for evaluating watermark robustness against learned removal at the representation level, not only against conventional image edits.

cs.CV↗

arXiv2026

Early Near-Infrared Excess and Rapid Disk-Corona Evolution in the Tidal Disruption Event 2024aepd

We present multi-wavelength observations of the tidal disruption event (TDE) 2024aepd, spanning primarily the first $\sim$300 days after discovery. A prominent near-infrared (NIR) excess is detected as early as $\sim$40 days. Its nearly flat power-law spectrum strongly deviates from the Rayleigh-Jeans tail of the UV-optical blackbody. Although a conventional dust-echo origin cannot be completely ruled out, free-free emission from a reprocessing photospheric envelope provides a more plausible explanation. The spectral break between the UV-optical and NIR components shifts to higher frequencies, while the inferred density-profile index remains nearly constant, suggesting evolving reprocessing conditions within a broadly unchanged density structure. In addition, the X-ray spectrum is initially dominated by a thermal disk component accompanied by a hard excess. From $\sim$178 days onward, the spectrum becomes power-law dominated and subsequently hardens, indicating the rapid emergence and strengthening of a hot corona. These results provide evidence for frequency-dependent reprocessing at early times and for the rapid development of a disk-corona system, placing new constraints on the structure and evolution of the reprocessing layer around supermassive black holes.

astro-ph.HE↗

arXiv2026

Qwen-Audio-3.0-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.

cs.CL↗

arXiv2026

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes. The proposed framework supports three tasks: Lyrics-to-Song Generation, which generates complete songs from text descriptions, lyrics, and musical attributes; Instrumental Music Generation, which creates music without vocals; and Cover Song Generation, which reinterprets existing songs with different styles while preserving their melodic content. Architecturally, our system consists of four main components: a semantic-aware tokenizer, hybird-LM, FullDiT, and a two-level melody module. The tokenizer encodes audio into 8-codebook RVQ tokens for efficient discrete music representation. Based on these tokens, hybird-LM performs hierarchical autoregressive audio-token modeling for full-song generation. To improve audio fidelity, FullDiT performs full-song flow matching in a continuous VAE latent space conditioned on codec tokens, lyrics, and text captions. For cover song generation, the melody module extracts and discretizes melody cues from reference audio to guide generation while preserving the original melodic content. Finally, we investigate DPO, GRPO, and OPD as reward-based post-training strategies for hybird-LM and apply flow-based GRPO to FullDiT to improve musicality and rendering quality. Experimental results on a multilingual automatic benchmark, complemented by the Artificial Analysis Music with Vocals leaderboard, show that the proposed framework achieves competitive performance in the evaluated settings.

cs.SD↗

arXiv2026

TF-MossFormer: Integrating Convolution Gated Local-Global Attentions for Enhanced Time-Frequency Domain Monaural Speech Separation

Transformers with global attention capture long-range dependencies but can miss the fine-grained local continuity crucial for speech separation. We propose TF-MossFormer, a time-frequency transformer that combines local and global attention to jointly model short- and long-range contexts for monaural speech separation. At its core is a content-aware sliding-window attention mechanism that dynamically adapts receptive fields for stronger local interactions, avoiding the rigidity of static convolutions. Unlike time-domain chunk-based methods, TF-MossFormer leverages the 2D spectrogram to model structure along both time and frequency axes. Convolutional gating between attention layers further improves feature selection and information flow. TF-MossFormer achieves SI-SDRi of 22.6, 24.0, and 24.4 dB on WSJ0-2Mix with 5.9M, 16.9M, and 25.4M parameters, respectively, outperforming prior approaches.

cs.SD↗

arXiv2026

GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark

While modern ASR systems achieve low error rates on high-resource benchmarks, such performance often overestimates real-world robustness. Existing evaluations address challenges in isolation, lacking a unified benchmark for domain terminology, age variation, dialects, accents, and low-resource languages, particularly across the Middle East and Southeast Asia, representing over one billion under-evaluated speakers. To address this gap, we introduce GigaSpeechBench, a comprehensive multilingual and multidimensional in-the-wild ASR & AST benchmark comprising 680 hours of human-annotated speech. It features five modules: (1) 12 low-resource Middle Eastern and Southeast Asian languages, plus challenging Japanese and Korean; (2) 6 Chinese dialects; (3) 6 English accents; (4) dense terminology across 12 vertical domains for Chinese and English; and (5) older adult and child speech. We further provide human-annotated Chinese and English translations for 11 languages to support AST evaluation. Extensive evaluations of leading foundation models and commercial APIs reveal significant performance degradation in these challenging settings, exposing critical evaluation blind spots.

eess.AS↗

arXiv2026

Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models

Attention collapse in autoregressive language models -- manifested as repetitive token loops where the model becomes trapped in self-reinforcing attractors -- is a persistent pathology that existing decoding-time heuristics fail to address at its root cause. We present a principled framework that penalises or compensates anomalous confidence arising from collapsed generation patterns, by comparing a token's observed frequency against its corpus prior through an adjacent-conditional probability construction. The resulting self-normalising penalty ratio $R=f(m,n,p)/f(np,n,p)$ requires no ad hoc standardisation and admits a closed-form logit offset with zero approximation error. The correction is isolated from the loss gradient and accumulated into a frozen output-layer bias via exponential moving average, enabling deployment as a repair mechanism for models that have already collapsed without requiring intrusive modifications to standard training pipelines. Experimental validation on a 1.5B-parameter model demonstrates that the frozen-bias mechanism can rescue a model already trapped in a collapsed attractor, reducing 2-gram repetition from 0.073 to near 0 while preserving generation quality.

cs.AI↗

arXiv2026

$J$ and $H$ band sky brightness measurements from polar day to polar night at Dome A, Antarctica

The near-infrared (NIR) sky brightness is a fundamental parameter for evaluating the performance of ground-based infrared observatories. Dome~A on the Antarctic plateau offers exceptional atmospheric conditions, yet its NIR sky background has not been continuously monitored. We present the first continuous $J/H$-band measurements of the sky background at Dome~A from polar day to polar night, and characterize their median levels and temporal variability. The Antarctic Infrared Binocular Telescope (AIRBT), operating in the $J$ and $H$ bands, obtained continuous fixed-pointing observations from February to May 2024, which were used to measure the NIR sky background. The median sky brightness is $5.2/2.9$ and $15.3/13.4~\mathrm{mag~arcsec^{-2}}$ in $J/H$ bands during daytime and nighttime, respectively. The twilight--nighttime boundaries occur at solar elevations of $-9.3^\circ$ in $J$ and $-7.4^\circ$ in $H$. At the same solar elevation, the NIR sky background during the polar night is darker by about $0.1$ and $0.4~\mathrm{mag~arcsec^{-2}}$ in the $J$ and $H$ bands compared with the period of regular day--night alternation. During the polar-night period, the nighttime sky brightness in the $H$ band shows a more evident association with the sunspot number, while the corresponding trend in the $J$ band is weaker. These results reveal systematic differences in sky background between polar and non-polar environments and between polar night and regular day--night cycles. The measured sky brightness may be elevated, as the observations were conducted near solar maximum, highlighting the importance of long-term monitoring across the solar cycle.

astro-ph.IM↗

arXiv2026

AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint training of multiple audio generation tasks faces an asymmetric text--audio mismatch: speech transcripts align to specific time spans and demand tight, time-aligned attention, whereas sound and music captions describe only overall semantics and rely on diffuse, holistic attention; mixing the two disproportionately degrades sound and music generation. We address this asymmetry at two levels: a data reformulation strategy that unifies all three tasks under a single description-style conditioning interface, and a novel architecture Asymmetric Mixture-of-Modality-Experts (A-MoME), which adds a dedicated residual expert for speech while sound and music share the backbone, incurring no inference overhead on non-speech inputs. Experimental results demonstrate that AudioCALM matches modality-specific state-of-the-art and outperforms prior unified baselines on speech, sound, and music generation benchmarks.

eess.AS↗

arXiv2026

Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models

While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degrade when the target emotion conflicts with the textual semantics. We propose a Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) method with dynamic scales based on the degree of inconsistency between the text emotion and the explicit speech emotion, replacing the dropout condition with the text emotion. We also distill the CCG-CFG guidance signal using a hard-sample mining strategy, improving the TTS model's emotional alignment capability. Evaluations on five emotional corpora and two TTS benchmarks show that our approaches applied to CosyVoice2 achieve up to a 12% absolute improvement in emotion-recognition accuracy and a 10% relative improvement in subjective scores, outperforming baselines including HierSpeech++, Qwen3-TTS, and original CosyVoice2, while preserving intelligibility, naturalness, and high speech quality.

cs.CL↗