arXiv subjects

Junbo Zhang

Publications and source records attributed to Junbo Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Carbon in J0815+4729: Casting A Shadow of Doubt on the Interpretation of CH Absorption in the Most Primitive Stars

We revisit the carbon abundance in the primitive iron-poor star J0815+4729 ([Fe/H] $=$ $-$5.49). J0815+4729 is so carbon-enhanced and oxygen-rich that, in addition to CH and C$_{2}$ molecular lines, weaker neutral atomic transitions are measurable in its spectrum, providing a unique opportunity to explore the line formation of C I and O I transitions in such an extremely iron-deficient star. Based on high-resolution spectroscopy and newly constructed atomic models for carbon and oxygen, we present the first investigation to derive carbon and oxygen abundances of this hyper iron-poor star from neutral atomic transitions under non-local thermodynamic equilibrium (NLTE) conditions. The carbon abundance derived from C I lines is A(C)$_{\rm NLTE} = 8.08 \pm 0.07$, consistent with that inferred from C$_{2}$ lines (A(C)$_{\rm LTE} = 7.96 \pm 0.08$), but around 0.6 dex higher than the value from CH lines (A(C)$_{\rm LTE} = 7.47 \pm 0.17$). Since CH lines are the most commonly-used carbon abundance indicator for extremely metal-poor stars, this result casts doubt on the quantitative interpretation of CH absorption in the most primitive stars. We confirm that J0815+4729 is one of the most carbon-enhanced stars with [Fe/H] $\le$ $-$4.5 known to date. We have also determined A(O)$_{\rm NLTE}$ as 7.25 $\pm$ 0.11, with NLTE corrections of around $-$0.11\,dex. The carbon-to-oxygen ratio of the star is [C/O] $=$ 1.06 $\pm$ 0.11.

astro-ph.SR↗

arXiv2026

DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning

Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific fine-tuning can also weaken the safety guardrails of aligned LLMs. A widely adopted strategy for preserving safety during fine-tuning is to incorporate safety data. Although previous studies have shown that randomly mixing safety data can alleviate safety degradation, the underlying principle determining why some safety examples are more effective than others still remains unclear. In this paper, we propose DataRx, a missingness-aware sampling method for selecting safety-critical examples. DataRx is based on the hypothesis that a safety sample is more effective when the selected examples provide safety signals that fill the missing parts of LLMs' safety capabilities. DataRx's key insight is leveraging high-dimensional hidden representations rather than discrete tokens to quantify the safety signal gap between the target model's native response and the safety reference response. The results show that, with only 1% additional safety samples from BeaverTails, DataRx reduces the average attack success rate of Llama3-8B-Instruct across seven downstream tasks from 59.23% under random sampling to 13.70%. In addition, DataRx can be combined with the existing safety data synthesis method to further enhance safety defenses during fine-tuning. We hope that DataRx will inspire more data-centric defense research.

cs.CL↗

arXiv2026

DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization

Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weight updates. This pipeline optimizes an intermediate representation but deploys multi-layer weight updates whose joint effect through the true forward pass is never itself optimized: regardless of how anchors are set or propagated, each update comes from a local solve, so propagation-induced attenuation and distortion go uncorrected, leaving a closure gap between anchor targets and realized edits. We propose DOW-KE, an anchor-free method built on a single principle: what is optimized must be exactly what is deployed. DOW-KE backpropagates the final editing objective through the complete model, jointly optimizing the updates of all edited layers so cross-layer propagation and coupling enter every gradient step. The same principle dictates where preservation resides: embedding the preservation projection in the update parameterization, inside the computation graph, makes every gradient act on the deployed update; post-hoc constraints would reopen the gap, and the constrained search keeps edits clear of protected knowledge. In large-scale sequential editing on two datasets and three models, DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six model-dataset settings among the evaluated baselines.

cs.LG↗

arXiv2026

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues. In this paper, we propose DataShield to efficiently and effectively identify potential safety-degrading samples. Our key intuition is based on the observation that benign fine-tuning increases the overall response compliance of LLMs. DataShield's key technical insight is to quantify each sample's contribution to the model's compliance behavior as its safety degradation score. DataShield consists of three core components: (1) Compliance Vector Extraction, which captures the LLM's compliance behavior tendency; (2) a novel Compliance-Aware Score (CAS), which automatically identifies the optimal safety-critical layer; and (3) Safety-degrading Sample Filtering, which quantifies the projection shift of training data along the compliance direction. Extensive experimental evaluation on Llama3-8B, Llama3.1-8B, and Qwen2.5-7B using the Alpaca and Dolly benign datasets validates our method's effectiveness in identifying high-risk and low-risk data subsets. We also observe that open-ended question answering is more likely to trigger safety degradation, and corresponding responses tend to be longer. We hope this work can provide new insights into data-centric defense methods. The source code is available at: https://github.com/ZJunBo/DataShield.

cs.CR↗

arXiv2026

Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text

Audio generation has long been fragmented, with speech, music, and sound effects produced by domain-specific models that fail to jointly generate coherent audio scenes from a single description. The key obstacles are insufficient fine-grained supervision for real-world mixed audio and limited acoustic representations for modeling concurrent audio components. We present Dasheng AudioGen, a unified framework for generating general mixed-audio scenes from text. Dasheng AudioGen introduces structured multi-view captions, which explicitly decouple complex acoustic scenes into complementary description views, thereby enabling fine-grained control over audio layers. Furthermore, we employ a high-dimensional unified semantic-acoustic representation as the shared latent space. It injects semantic priors that facilitate cross-modal training convergence, while its high-dimensional feature space provides sufficient capacity to disentangle and fuse concurrent audio components effectively. With these designs, a simple flow-matching DiT achieves high-quality end-to-end audio scene generation. We also establish a comprehensive evaluation pipeline for audio scene generation. Experiments demonstrate that Dasheng AudioGen achieves performance approaching real-world recordings in mixed-audio categories, while remaining competitive with specialized models in single-type generation tasks. Demos are available at https://nieeim.github.io/Dasheng-AudioGen-Web/.

cs.SD↗

arXiv2026

A Systematic NLTE Study of Very Metal-Poor Stars with Metallicity Down to $-4.3$ dex. II. Lithium Abundance and New Insight to the Lithium Plateau

Metal-poor stars are crucially important for understanding the early Galaxy, first stars, and the Universe. In this series of papers, we present a homogeneous non-local thermodynamic equilibrium (NLTE) abundances analysis of 12 elements for 103 very/extremely metal-poor (VMP/EMP) stars with metallicity down to $-4.3$ dex. The sample was selected from the LAMOST survey and observed by the high-resolution spectroscopy of Subaru. In this paper, we present the NLTE abundances and evolution of lithium in these stars. We report different lithium behaviors corresponding to different evolutionary stages and their signatures: 1) The Spite Plateau shows a slightly positive slope, indicating increasing lithium abundance with increasing metallicity. Most significantly, it appears to extend to lower metallicities as previously suggested, calling into question the reality of the so-called 'meltdown' at low metallicity; 2) We confirm a lithium plateau for lower red giant branch (LRGB) stars with A(Li) $= 1.13$ dex in our sample, while lithium abundance drops rapidly to A(Li)$<0.5$ as stars continue to evolve to higher stage. 3) We identify four Li-rich stars in our sample across different evolutionary stages, showing complex and multiple lithium production mechanisms in VMP/EMP stars. These findings suggest that early Galactic lithium enrichment results from a complex interplay between depletion and production processes.

astro-ph.SR↗

arXiv2026

ActivityEditor: Learning to Synthesize Physically Valid Human Mobility

Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regions where historical trajectories are unavailable or restricted. To bridge this gap, we propose \textbf{ActivityEditor}, a novel dual-LLM-agent framework designed for zero-shot cross-regional trajectory generation. Our framework decomposes the complex synthesis task into two collaborative stages. Specifically, an intention-based agent, which leverages demographic-driven priors to generate structured human intentions and coarse activity chains to ensure high-level socio-semantic coherence. These outputs are then refined by editor agent to obtain mobility trajectories through iteratively revisions that enforces human mobility law. This capability is acquired through reinforcement learning with multiple rewards grounded in real-world physical constraints, allowing the agent to internalize mobility regularities and ensure high-fidelity trajectory generation. Extensive experiments demonstrate that \textbf{ActivityEditor} achieves superior zero-shot performance when transferred across diverse urban contexts. It maintains high statistical fidelity and physical validity, providing a robust and highly generalizable solution for mobility simulation in data-scarce scenarios. Our code is available at: https://anonymous.4open.science/r/ActivityEditor-066B.

cs.AI↗

arXiv2026

Closeby Habitable Exoplanet Survey (CHES). V. Planetary Parameters Derived from Angular Separation Variations

The Closeby Habitable Exoplanet Survey (CHES) aims to achieve microarcsecond-level astrometry of about one hundred nearby FGK-type stars within 10 parsecs to detect Earth-like planets. Such precision exceeds the capability of absolute astrometry relying on Gaia catalogs, whose positional accuracy degrades over time due to error propagation from stellar motion and epoch offsets, limiting their use in microarcsecond-level detection. Traditional relative astrometry depends on positional components along right ascension and declination, requiring precise knowledge of field rotation and satellite attitude, which introduces additional errors. To address this, we propose a new relative measurement model based solely on variations in the length of angular separation between the target and reference stars, independent of direction. The model incorporates effects such as proper motion, parallax, radial velocity, light aberration, gravitational lensing, and planetary perturbations, enabling reconstruction of planetary orbits and masses. This approach enhances measurement stability and precision, providing a framework that is not entirely dependent on the Gaia catalog and suitable for CHES and other future high-accuracy astrometric missions.

astro-ph.EP↗

arXiv2026

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in this domain is hindered by existing datasets, which lack the scale and descriptive granularity required to train truly versatile models. To address this gap, we introduce ACAVCaps, a new large-scale, fine-grained, and multi-faceted audio captioning dataset. Derived from the ACAV100M collection, ACAVCaps is constructed using a multi-expert pipeline that analyzes audio from diverse perspectives-including speech, music, and acoustic properties-which are then synthesized into rich, detailed descriptions by a large language model. Experimental results demonstrate that models pre-trained on ACAVCaps exhibit substantially stronger generalization capabilities on various downstream tasks compared to those trained on other leading captioning datasets. The dataset is available at https://github.com/xiaomi-research/acavcaps.

eess.AS↗

arXiv2026

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio Language Models (LALMs). While LALMs have shown remarkable understanding of complex acoustic scenes, their performance depends on the semantic richness of the underlying audio encoder representations. This challenge addresses the integration gap by providing a unified generative evaluation framework, XARES-LLM, which assesses submitted encoders across a diverse suite of downstream classification and generation tasks. By decoupling encoder development from LLM fine-tuning, the challenge establishes a standardized protocol for general-purpose audio representations that can effectively be used for the next generation of multimodal language models.

cs.SD↗

arXiv2026

Spectral Dataset of Stripped-Envelope Supernovae from the Tsinghua Supernova Group

The extent of envelope stripping in the progenitor stars is directly reflected in the diversity of spectral features observed in stripped-envelope supernovae (SESNe). Through extensive spectral observation and analysis, we aim to clarify the statistical differences between the subclasses of SESNe. The Tsinghua Supernova group obtained 249 optical spectra of 62 SESNe during the years from 2010 to 2020, covering phases from $-$16 to over 190 days relative to maximum light. Most spectra were obtained during the photospheric phases after the supernova explosion. For each spectrum, the pseudo-equivalent widths (pEWs) and blueshift velocities of principal lines were measured. We further investigated the common spectral features by analysing their velocity and strength correlations across all subtypes. We identify the feature near 6200~\AA\ in SNe Ib as H$\mathrm{\alpha}$ through comparison with SNe IIb and Ic, which resolves inconsistent literature interpretations. Our finding reveals prevalent residual hydrogen in SNe Ib, further supporting a continuous stripping sequence from SNe IIb to Ib. We observe a trend in increasing velocity among different subtypes of stripped-envelope SNe, with SNe IIb exhibiting the lowest line velocities, followed by Ib, Ic, and Ic-BL. Typically, the O~I lines in SNe Ic/Ic-BL are stronger than those seen in SNe IIb/Ib. In nebular phases, the [Ca II] emission dominates over [O I] in SNe IIb/Ib while [O I] is stronger in SNe Ic, including the He-rich SN 2016coi. This spectral dichotomy implies that progenitors of SNe Ic (BL) have more massive CO cores and hence higher initial masses.

astro-ph.HE↗

arXiv2026

DashengTokenizer: One layer is enough for unified audio understanding and generation

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which train acoustic tokenizers and subsequently integrate frozen semantic knowledge, our method inverts this paradigm: we leverage frozen semantic features and inject acoustic information. In linear evaluation across 22 diverse tasks, our method outperforms previous audio codec and audio encoder baselines by a significant margin while maintaining competitive audio reconstruction quality. Notably, we demonstrate that this acoustic injection improves performance for tasks such as speech emotion recognition, music understanding, and acoustic scene classification. We further evaluate the tokenizer's generative performance on text-to-audio (TTA), text-to-music (TTM), and speech enhancement (SE). Our approach surpasses standard variational autoencoder (VAE)-based methods on TTA and TTM tasks, while its effectiveness on SE underscores its capabilities as a general-purpose audio encoder. Finally, our results challenge the prevailing assumption that VAE-based architectures are a prerequisite for audio synthesis. Checkpoints are available at https://huggingface.co/mispeech/dashengtokenizer.

cs.SD↗

arXiv2026

Scaling World Model for Hierarchical Manipulation Policies

Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework \our{} that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsual Subgoal TAsk decomposition VISTA. Our hierarchical framework \our{} consists of a world model as the high-level planner and a VLA as the low-level executor. The high-level world model first divides manipulation tasks into subtask sequences with goal images, and the low-level policy follows the textual and visual guidance to generate action sequences. Compared to raw textual goal specification, these synthesized goal images provide visually and physically grounded details for low-level policies, making it feasible to generalize across unseen objects and novel scenarios. We validate both visual goal synthesis and our hierarchical VLA policies in massive out-of-distribution scenarios, and the performance of the same-structured VLA in novel scenarios could boost from 14% to 69% with the guidance generated by the world model. Results demonstrate that our method outperforms previous baselines with a clear margin, particularly in out-of-distribution scenarios. Project page: \href{https://vista-wm.github.io/}{https://vista-wm.github.io}

cs.RO↗

arXiv2025

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

cs.AI↗

arXiv2025

Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention

Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vulnerabilities undermine the reliable application of LLMs in real-world scenarios. To enhance LLM safety, various jailbreak defense methods have been proposed to guard against harmful outputs. However, improvements in model safety often come at the cost of severe over-refusal, failing to strike a good balance between safety and usability. This phenomenon is a critical reliability degradation issue in LLM intelligent systems, failing to strike a good balance between safety defense effectiveness and system usability reliability. In this paper, we first analyze the causes of over-refusal from a representation perspective, revealing that LLMs are unable to effectively distinguish between over-refusal samples and malicious samples. Based on this, we propose to mitigate overrefusal by intervening in the safety representation space of LLMs. Our method incorporates two core strategies: (1) OverlapAware Loss Weighting, which determines the erasure weight for malicious samples by quantifying their similarity to overrefusal samples in the representation space, and (2) ContextAware Augmentation, which supplements the necessary context for rejection decisions by adding harmful prefixes before rejection responses. Experiments demonstrate that our method achieves a better trade-off between mitigating over-refusal and maintaining safety, compared with existing approaches. This paper also aims to encourage researchers to consider the reliability of defending methods against jailbreak attacks from both the perspectives of safety and over-refusal.

cs.CR↗

arXiv2025

JoyAgent-JDGenie: Technical Report on the GAIA

Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks, yet existing systems often focus on isolated improvements without a unifying design for robustness and adaptability. We propose a generalist agent architecture that integrates three core components: a collective multi-agent framework combining planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing. Evaluated on a comprehensive benchmark, our framework consistently outperforms open-source baselines and approaches the performance of proprietary systems. These results demonstrate the importance of system-level integration and highlight a path toward scalable, resilient, and adaptive AI assistants capable of operating across diverse domains and tasks.

cs.CL↗

arXiv2025

GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values

The ubiquity of missing data in urban intelligence systems, attributable to adverse environmental conditions and equipment failures, poses a significant challenge to the efficacy of downstream applications, notably in the realms of traffic forecasting and energy consumption prediction. Therefore, it is imperative to develop a robust spatio-temporal learning methodology capable of extracting meaningful insights from incomplete datasets. Despite the existence of methodologies for spatio-temporal graph forecasting in the presence of missing values, unresolved issues persist. Primarily, the majority of extant research is predicated on time-series analysis, thereby neglecting the dynamic spatial correlations inherent in sensor networks. Additionally, the complexity of missing data patterns compounds the intricacy of the problem. Furthermore, the variability in maintenance conditions results in a significant fluctuation in the ratio and pattern of missing values, thereby challenging the generalizability of predictive models. In response to these challenges, this study introduces GeoMAE, a self-supervised spatio-temporal representation learning model. The model is comprised of three principal components: an input preprocessing module, an attention-based spatio-temporal forecasting network (STAFN), and an auxiliary learning task, which draws inspiration from Masking AutoEncoders to enhance the robustness of spatio-temporal representation learning. Empirical evaluations on real-world datasets demonstrate that GeoMAE significantly outperforms existing benchmarks, achieving up to 13.20\% relative improvement over the best baseline models.

cs.LG↗

arXiv2025

MiDashengLM: Efficient Audio Understanding with General Audio Captions

Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.

cs.SD↗