Search arXiv⌕ Search

arXiv subjects

Jialu Li

Publications and source records attributed to Jialu Li.

At least 19 recordsLinked to original sources
arXiv2026

EditAgent: Rethinking Agentic Image Editing

Agentic image editors decompose complex requests into steps, but when a step fails, they mostly retry with the same narrow set of tools and a judge that scores each output by eye directly. We argue that such agents are bounded by two spaces: the action space of what the agent can do, and the observation space of what its judge can see. On our expert-annotated benchmark, a general-purpose editor yields no usable result in over 40% of the cases, and no judge is reliable across edit types. We present EditAgent, which expands both spaces. It routes each step to general editors and specialized methods, and attaches to each candidate a verification record. With these records, off-the-shelf VLM judges outperform finetuned reward models. Candidates are generated in parallel and judged in one listwise call: experts prefer this to sequential refinement in 78.5% of decided comparisons, at no more than half the judge calls. EditAgent improves two open-weight editors on three benchmarks and serves as a data engine for training stronger editors.

cs.CV↗
arXiv2026

OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning

We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native tool use. Rather than passively processing an entire audio-visual sequence in a single forward pass, OmniSeek makes evidence acquisition part of the reasoning process: it dynamically decides whether to look or listen, and over which temporal window, to retrieve sparse but critical evidence across different modalities within long contexts. Through an iterative multi-turn protocol, the retrieved raw audio or visual segments are appended back into the context to support subsequent reasoning. To cold-start this capability, we build a data engine that synthesizes OmniTraj-170K, a corpus of multi-hop Chain-of-Thought trajectories with interleaved audio and visual evidence. We first supervise the model on these trajectories to instill multi-turn tool-use behavior, and then further optimize the policy via a two-stage reinforcement learning with verifiable rewards. Moreover, we introduce an Audio-Visual Necessity objective that explicitly rewards successful trajectories whose reasoning depends on both modalities, discouraging single-modality shortcuts. Extensive experiments across a wide range of benchmarks demonstrate that OmniSeek learns adaptive cross-modal evidence seeking and consistently improves audio-visual reasoning performance.

cs.CV↗
arXiv2026

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence.

cs.RO↗
arXiv2026

Time Delay System for Sequence Modeling

Existing sequence models share a critical limitation: they lack an explicit, interpretable mechanism for content-aware temporal recall. LSTMs compress everything into a single hidden state, thereby losing information about specific past events. Transformers attend to all tokens indiscriminately at quadratic cost, while state-space models like Mamba compress history into a fixed-dimensional state without explicit content-addressable memory. To address this gap, we introduce a novel framework grounded in nonlinear time-delay systems, in which the effective delay is dynamically estimated based on the semantic similarity between current and historical inputs. Our approach features three key innovations: (i) a differentiable semantic lag estimator that computes content-aware soft attention weights over history, producing a weighted historical context and similarity score; (ii) a diagonal state space with closed-form cumulative sum solution, achieving O(1) per-step complexity with no sequential loops; and (iii) an interpretable fuzzy semantic modulation mechanism that learns context-dependent rules for balancing instantaneous processing versus historical recall, where rule centers correspond to prototypical semantic contexts. Experimental results on text classification and generation outperform state-of-the-art methods.

cs.CL↗
arXiv2026

Speech Language Models for Full-Meeting Speaker Diarization: Capabilities and Limitations

Recent advances in Speech Language Models (SpeechLMs), which integrate large language models with speech foundation models, have enabled unified sequence modeling of speech processing tasks. However, many SpeechLM-based approaches to speaker diarization (SD) are tightly coupled with automatic speech recognition (ASR) and evaluated using word-level metrics, making it difficult to assess SD performance independent of ASR accuracy. In this work, we investigate ESPnet-SpeechLM as a token-based backbone for generating SD hypotheses, formulating SD as autoregressive generation of structured tokens conditioned on acoustic input. We systematically compare two output representations: an event-based representation that explicitly models speaker turn onset and offset timestamps, and a frame-based representation that predicts frame-level speaker activity. To provide structured conversational cues, we further incorporate auxiliary tasks including speech activity detection, overlapped speech detection, and speaker turn counting within the output sequence. Across multiple meeting datasets, we find that event-based representations produce more stable and consistent SD outputs than frame-based representations. Our analysis shows that outputs generated by SpeechLMs encode useful temporal SD structure, but full-meeting SD remains limited by recording-level speaker tracking and overlap-related misses. Explicit speaker-linking post-processing substantially reduces speaker confusion, suggesting that robust SpeechLM-based SD requires persistent speaker tracking and overlap-aware generation.

eess.AS↗
arXiv2026

Age-Aware Adapter Tuning for Children's Speech Recognition

Children's automatic speech recognition (ASR) remains challenging because child speech differs from adult speech and varies substantially across developmental stages. While adapter tuning provides a promising way to adapt large pretrained ASR models to children's speech, a single shared child adapter may not fully capture age-dependent variation. In this work, we present one of the first systematic studies of age-aware adapter tuning for child ASR, focusing on speech from children aged 3-12 and older. We propose age-specialized adapters trained separately for different age groups and compare them with a unified age-conditioned FiLM adapter. With ground-truth age routing, age-specialized adapters improve over a strong shared child adapter baseline from 12.5% to 12.3% overall word error rate (WER) and from 16.4% to 16.1% macro-age WER, while consistently improving WER across all four known-age groups. We further show that predicted-age routing remains close to ground-truth routing, achieving 12.3% overall WER and 16.3% macro-age WER without ground-truth age labels at inference. In contrast, unified FiLM conditioning does not consistently improve over the shared child adapter, indicating that a single unified adapter may be insufficient to capture developmental variation in child speech.

eess.AS↗
arXiv2026

The JWST Proto-PAH Project: Detection of the methyl radical CH$_{3}$ in the highly evolved C-rich object SMP LMC 011

We report the first detection of the neutral methyl radical CH$_3$ in a highly evolved C-rich object, SMP LMC 011, using JWST MIRI/MRS. CH$_3$ is well fitted by an excitation temperature of $T_{\rm ex} \simeq$~190\,K and a column density of $N_{\rm tot}(\mathrm{CH_3}) \simeq 5.6\times10^{17}$ cm$^{-2}$. We also report the non-detection of ethane (C$_2$H$_6$), consistent with CH$_3$ reacting preferentially with unsaturated radicals rather than self-recombination, which may be inefficient in SMP LMC 011. Combined with the exceptionally large benzene column density of SMP LMC 011, this supports a methyl-addition route from benzene towards alkyl-substituted aromatics. We propose that the high CH$_3$ abundance is driven by the erosion of hydrogenated amorphous carbon (HAC) dust grains in the dense warm torus by UV photons from the central star and/or by shocks, which release CH$_3$ directly into the gas phase. These results establish CH$_3$ as a key reactive intermediate in the formation of complex hydrocarbons in C-rich circumstellar environments. Chemical models that incorporate methyl-addition reactions are needed for a better understanding of PAH formation pathways in evolved stars. The potential detection of alkyl-substituted aromatics such as toluene (C$_7$H$_8$) and ethylbenzene (C$_8$H$_{10}$) in C-rich evolved stars would provide direct confirmation of CH$_3$-driven aromatic growth in circumstellar environments.

astro-ph.SR↗
arXiv2026

Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics

Many emerging video language modeling tasks require systems to move beyond clip-level abstraction and model visual content as it unfolds over extended time horizons. However, most existing video datasets rely on coarse or sparsely aligned supervision, which compresses temporal variation and limits the ability of models to learn reusable representations of continuous visual dynamics. We introduce Kairos, a video dataset for video-language modeling with time-resolved annotations. Kairos consists of long-duration videos, ranging from ten minutes to half an hour, annotated with fine-grained temporal alignment. The annotations capture ongoing actions, entity appearances and attributes, interactions, and evolving contextual cues along the video timeline. This time-resolved structure supports fine-grained evaluation, long-range modeling and reasoning, instruction data construction, representation learning, and video generation. Kairos provides a general-purpose foundation for modeling visual experiences over time.

cs.CV↗
arXiv2026

Error-Driven Scene Editing for 3D Grounding in Large Language Models

Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources, leaving inherent grounding biases unresolved. To address this, we propose 3D scene editing as a key mechanism to generate visual counterfactuals that mitigate these biases through fine-grained spatial manipulation, without requiring costly scene reconstruction or large-scale 3D data collection. Furthermore, to make these edits targeted and directly address the specific weaknesses of the model, we introduce DEER-3D, an error-driven framework that diagnoses grounding failures and generates targeted counterfactual training supervision via a structured "Decompose, Diagnose, Edit, and Retrain" loop. Specifically, given a grounding failure, DEER-3D first identifies the predicate-level error (e.g., attribute or spatial relation). It then performs minimal predicate-aligned scene edits, such as recoloring or repositioning, and constructs aligned question-answer pairs that explicitly target the failed predicate, forming targeted counterfactual training examples. We evaluate our editing pipeline across multiple benchmarks for 3D grounding and scene understanding tasks, consistently demonstrating improvements across all grounding datasets through iterative refinement (4-6% gains). DEER-3D underscores the effectiveness of targeted, error-driven scene editing in bridging linguistic reasoning with spatial grounding in 3D LLMs.

cs.CV↗
arXiv2026

Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning

Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts. We present a family-conditioned, multi-tier audio tagger that combines a LoRA-finetuned Whisper encoder with a lightweight, target-speaker-aware Transformer for long-context inference and framewise prediction across tiers. To improve temporal coherence, we incorporate a simple sequence-level smoothing loss, and to enhance robustness across households, we introduce a factorized speaker-token design with a shared tier token and a learned family-specific offset, reducing family bias and promoting generalizable representations. Together, these choices enable efficient and effective infant-centered audio tagging of daylong audio recordings in home environments.

eess.AS↗
arXiv2026

Boron-assisted synthesis of compositionally complex amorphous oxides via short-range-order-constrained generative design

Engineering short-range atomic order in amorphous materials offers a promising yet still underexplored route to high-performance solids. Here, we establish a boron-assisted amorphization strategy through ApolloX, a theory-guided, short-range-order-constrained generative framework for identifying low-energy amorphous configurations in compositionally complex multimetal BOx systems. Using FeCoNiMoBOx as a representative model platform, ApolloX predicts an ensemble of candidate amorphous configurations across systematically varied boron contents. Ab initio molecular dynamics simulations based on these configurations show that increasing boron content suppresses atomic diffusion and disfavors crystallization, with the stabilization of BO3-centered local motifs emerging as a key structural feature associated with enhanced amorphization propensity. Guided by these predictions, we synthesize three representative FeCoNiMoBOx compositions with distinct boron contents and use synchrotron-based scattering and electron microscopy to verify compositional fidelity, structural homogeneity, and the targeted amorphous features, thereby experimentally validating the boron-regulated structural evolution predicted by theory. Beyond this representative system, the same strategy is extended to a broader library of multimetal BOx amorphous compositions spanning diverse metal combinations and boron loadings, demonstrating that the boron-assisted route is not limited to a single FeCoNiMoBOx family but is broadly transferable across compositionally complex amorphous oxides. Overall, our results establish boron incorporation as a practical design variable for tuning short-range order and amorphization in multicomponent oxides, and provide a general framework for the theory-guided discovery of compositionally complex amorphous materials with tunable properties.

cond-mat.mtrl-sci↗
arXiv2026

The EDGE-CALIFA Survey: Star Formation Efficiency and Galaxy Quenching across 62 Main Sequence, Green Valley, and Red Galaxies

We present GBT-EDGE, a new CO(1-0) survey using the Green Bank Telescope to map 62 nearby (10-140 Mpc) galaxies spanning the star-forming main sequence (SFMS), green valley, and red sequence. The galaxy sample is selected from the CALIFA survey with integral field spectroscopy (IFS), which provides a representative census of local galactic environments. Combining the CO dataset with CALIFA's optical IFS measurements, we derive molecular gas masses, star formation rates (SFR), metallicities, and stellar mass densities to measure star formation efficiency (SFE) and investigate the physical drivers of galaxy quenching. We obtain a median molecular gas depletion time of $2.10^{+2.35}_{-1.31}$, $6.90^{+17.00}_{-3.67}$, and $127.7^{+201.6}_{-113.4}$ Gyr for our sample of main sequence, green valley, and red galaxies, respectively, assuming a Galactic CO-to-H2 conversion factor. By applying various conversion factor prescriptions, we also confirm a systematic decrease of SFE with galaxy's offset below the SFMS, regardless of the adopted prescription. This suggests that the low SFR in some quenched galaxies is primarily driven by suppressed SFE rather than an absence of molecular gas. Our results provide evidence that galaxies below the main sequence can retain substantial molecular gas reservoirs comparable to star-forming galaxies, but they exhibit longer depletion times and form stars inefficiently, possibly due to the combined effects of low gas density and morphological quenching mechanisms.

astro-ph.GA↗
arXiv2026

U$^2$Mamba: A Two-level Nested U-structure Mamba for Salient Object Detection

Mamba-based models have emerged as a promising alternative for salient object detection (SOD), offering significant advantages in modeling long sequences. However, existing models often fail to explore contextual information and the depth of the entire architecture. This paper introduces U$^2$Mamba, a powerful and innovative U-structured network for salient object detection. We propose multiscale Mamba U-blocks (MMUBs) that enhance the model depth to improve local feature extraction capabilities. Our newly developed nested U-structure, incorporating MMUBs, enables the network to integrate various receptive fields from shallow and deep layers, thereby collecting richer contextual information and longer-range data without being constrained by resolution. Instead of using the traditional deep supervision scheme and top-level supervised training, we propose a hierarchical training supervision method where the loss is computed at each level during the training process. Extensive experiments demonstrate that U$^2$Mamba achieves highly competitive performance against state-of-the-art methods. The source code is available at \url{https://github.com/JL021/U2Mamba}.

cs.CV↗
arXiv2026

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

Recent approaches for video generation with camera control often create anchor videos (i.e., rendered videos that approximate desired camera motions) to guide diffusion models as a structured prior, by rendering from estimated point clouds following camera trajectories. However, errors in point cloud and camera trajectory estimation often lead to inaccurate anchor videos with higher training cost and low efficiency, as the model is forced to compensate for rendering misalignments. To address these limitations, we introduce EPiC, an efficient and precise camera control learning framework that constructs well-aligned training anchor videos without the need for camera pose or point cloud estimation. Concretely, we create highly precise anchor videos by masking source videos based on first-frame visibility, which ensures strong alignment, eliminates the need for camera/point cloud estimation, and thus can be readily applied to any in-the-wild video. Furthermore, we introduce Anchor-ControlNet, a lightweight module that integrates anchor video guidance in visible regions to pretrained video diffusion models, with less than 1% of additional parameters. EPiC achieves efficient training with substantially fewer parameters, training steps, and less data, and generalizes robustly to anchor videos made with point clouds at test time, enabling precise 3D-informed camera control. EPiC achieves SoTA performance on RealEstate10K and MiraData for I2V camera control task. Notably, EPiC also exhibits strong zero-shot generalization to video-to-video (V2V) scenarios.

cs.CV↗
arXiv2026

FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition

Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-quality datasets and the high visual similarity between classes. To address these challenges, we first constructed a comprehensive dataset comprising 306 fruit categories with 116,233 samples. Moreover, we propose FruitEnsemble, a practical two-stage dynamic inference framework designed to overcome the generalization limitations of static single-model architectures. In the first stage, FruitEnsemble employs a validation-calibrated weighted ensemble of heterogeneous backbones to generate a robust Top-3 candidate pool. To tackle difficult samples, we introduce an expert arbitration mechanism: when ensemble confidence falls below 0.6, a multimodal large language model (MLLM) is triggered to perform rigorous visual verification by integrating external botanical descriptions using Chain-of-Thought (CoT) reasoning. Furthermore, we optimized the training pipeline with a hard sample-aware joint loss. Extensive experiments demonstrate that FruitEnsemble achieves a classification accuracy of 70.49\% and outperforms existing state-of-the-art models. Our framework provides an efficient, deployment-oriented solution for real-world agricultural visual sorting and quality inspection tasks.

cs.CV↗
arXiv2026

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Large Language Models (LLMs), this risk has intensified: LLMs are increasingly used for academic writing, but their tendency to fabricate citations (``ghost citations'') poses a systemic threat to citation validity. To quantify this threat, we develop \citeb, an open-source framework for large-scale citation verification, and conduct a comprehensive study of citation validity in the LLM era through three complementary experiments. First, we benchmark 13 LLMs on citation generation task in various research domains, finding that all models hallucinate citations at rate from 14.23\% to 94.93\%. Second, we analyze 2.2 million citations from 56,381 papers at AI/ML and Security venues (2020--2025), finding that 1.07\% of papers contain invalid citations, with an 80.9\% increase in 2025. Third, we survey 97 researchers, finding that 87.2\% use AI-powered tools in their workflows, 76.7\% of reviewers do not thoroughly check references, and 74.5\% view peer review as ineffective at catching citation errors. Based on these findings, we argue that ghost citations represent a systemic threat to academic integrity, and call for coordinated efforts from community to address this challenge.

cs.CR↗
arXiv2026

Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis

Automatic diagnosis of canine pneumothorax is challenged by data scarcity and the need for trustworthy models. To address this, we first introduce a public, pixel-level annotated dataset to facilitate research. We then propose a novel diagnostic paradigm that reframes the task as a synergistic process of signal localization and spectral detection. For localization, our method employs a Vision-Language Model (VLM) to guide an iterative Flow Matching process, which progressively refines segmentation masks to achieve superior boundary accuracy. For detection, the segmented mask is used to isolate features from the suspected lesion. We then apply Random Matrix Theory (RMT), a departure from traditional classifiers, to analyze these features. This approach models healthy tissue as predictable random noise and identifies pneumothorax by detecting statistically significant outlier eigenvalues that represent a non-random pathological signal. The high-fidelity localization from Flow Matching is crucial for purifying the signal, thus maximizing the sensitivity of our RMT detector. This synergy of generative segmentation and first-principles statistical analysis yields a highly accurate and interpretable diagnostic system (source code is available at: https://github.com/Pu-Wang-alt/Canine-pneumothorax).

cs.CV↗
arXiv2026

Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale

Goal-oriented vision-language navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize shortest-path trajectories, lacking effective exploration priors for training navigation agents. To address the above challenges, we present SID, a goal-oriented vision-and-language navigation learning approach with Self-Improving Demonstrations. Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories. The novel rollouts provide demonstrations with stronger exploration strategies to train a better agent, which in turn produces higher-quality agent demonstrations for the next round of training. We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations are highly transferable, elevating the performance ceiling across a variety of vision-and-language navigation tasks. Extensive experiments demonstrate that SID significantly boosts the exploration capabilities and generalization of navigation agents. The resulting agent achieves new state-of-the-art performance on goal-oriented vision-and-language navigation benchmarks, including REVERIE, SOON as well as strong transferability to object-goal navigation and VLN-CE. It notably achieves a 50.9% success rate on the unseen validation splits of SOON, surpassing prior leading approaches by a margin of 13.9%.

cs.CV↗