arXiv subjects

Guo Chen

Publications and source records attributed to Guo Chen.

At least 19 recordsLinked to original sources

arXiv2026

Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks

Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised paradigm. Recent EEG foundation models offer a route toward reusable representations, but most remain reconstruction-centered, assuming that EEG content predictable from local context is necessarily transferable neural information. Here we present INCEPT, an invariance-oriented EEG foundation model trained on over 11,000 hours of unlabelled clinical EEG. Rather than prioritizing signal recovery alone, INCEPT learns representation-level stability across correlated EEG observations, separating stable neural structure and essential subject-sensitive information from the nuisance variability that dominates scalp recordings while preserving subject-, state- and condition-discriminative information. We evaluate INCEPT on a broad-spectrum benchmark of ten datasets spanning three levels of post-acquisition EEG analysis: signal-level assessment, brain-state decoding, and brain-health evaluation. INCEPT ranks first among recent EEG foundation models on 26 of 30 linear-probing metrics and 24 of 30 fine-tuning metrics, and also surpasses strong task-specific specialist encoders across diverse downstream settings. Objective ablations and representation analyses further show that invariance-oriented pre-training improves transfer and organizes subject-sensitive neural representations beyond reconstruction alone. These results establish invariance learning as a promising principle for building reusable EEG foundation models.

cs.LG↗

arXiv2026

ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration

Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for evaluation across methods. Outcome-only benchmarks discard collaborations, whereas LLM-as-Judge evaluation requires additional, model-dependent inference and can vary with the LLM and rubric. We introduce a generalizable evaluation framework that maps native MAS traces into a shared space of unified collaboration graphs, enabling different methods to be evaluated under the same representation, reference set, and metric panel. Candidate graphs are compared with a query-specific reference forest. Each forest is a benchmark-provided collection of verified-success graphs: it records diverse ways in which representative MAS methods can complete the task, rather than prescribing a unique optimal process. Instantiating the framework as ForestBench, we filter $844$ collaboration-necessary queries from seven public datasets, precompute ten successful target-conditioned reference graphs per query, and evaluate six representative MAS frameworks. Controlled backbone, reference-construction, and perturbation studies test the stability and scope of evaluation. Once the benchmark forests are built, ForestBench scores a trace in milliseconds without further LLM inference, providing a reusable structural basis for comparing diverse MAS collaboration traces.

cs.AI↗

arXiv2026

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE.

cs.CV↗

arXiv2026

A Physically Driven Parameterisation of Multidimensional Atmospheres: Application to the JWST Phase Curve of WASP-121b

Understanding the multidimensional structure of strongly irradiated exoplanets is essential for interpreting their atmospheric dynamics, chemistry and energy transport, yet current analyses remain limited by the difficulty of extracting reliable phase-resolved spectra and by the lack of physically interpretable parameterisations for retrievals. We combine a data-driven eclipse-normalisation method with an analytical three-dimensional temperature parameterisation derived from radiative, advective and diffusive energy balance and controlled by a few characteristic timescales. Applied to JWST/NIRSpec G395H observations of WASP-121b, the method yields spectra consistent with conventional phase-curve fitting, while the parameterisation reproduces the large-scale thermal structures predicted by general circulation models. The preferred retrieval reveals a pronounced day--night contrast, a dayside thermal inversion extending to both limbs, an inversion over part of the nightside, and limb temperatures differing by several hundred kelvin. Dynamical transport strengthens with pressure, and the hotspot offset increases from $\sim4^\circ$ to $\sim9^\circ$ across the pressures probed by G395H. The confined dayside hot region and the small, pressure-dependent offsets lie closer to the $\sim$3~G GCM than to its non-magnetic counterpart, although Rayleigh drag cannot be excluded. The spectra also favour distinct dayside and nightside chemical states, with more nightside CH$_4$ than the cooler temperatures alone can explain, pointing to disequilibrium chemistry. The retrieved thermal structure further implies an inhomogeneous cloud distribution, with condensation favoured on the nightside and cooler morning limb. The framework provides a computationally efficient, physically interpretable path from spectroscopic phase curves to multidimensional atmospheric structure.

astro-ph.EP↗

arXiv2026

Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models

Visual information extraction (VIE) from visually rich documents remains challenging due to high layout variability and real-world impairments. Existing methods typically rely on sequential OCR pipelines or end-to-end models requiring extensive labeled data and layout-specific training, limiting their scalability.We propose a classification-guided large vision-language model (LVLM) framework for multi-type VIE that achieves high accuracy with minimal supervision. The approach decouples document-type classification from content extraction and employs in-context learning (ICL)-based dynamic prompt engineering to inject task-specific knowledge, enabling robust zero-shot inference across diverse layouts. From a theoretical perspective, the proposed method can be viewed as a form of conditional computation that reduces task uncertainty and improves information efficiency during prompt-based inference. Evaluated on a real-world bidding dataset with 16 certificate types, our zero-shot method (based on Qwen2.5-VL-7B) outperforms a strong supervised baseline by 18.35 percentage points in F1-score (86.43\% vs. 68.08\%) and 0.23 in normalized edit distance (0.90 vs. 0.67). Optional domain-specific fine-tuning further improves performance to 93.65\% F1 and 0.93 NED, demonstrating superior robustness against seals, watermarks, and low contrast. The framework offers an efficient, scalable solution for complex document understanding in office automation. Code is available at https://github.com/FairmeHIT/Multi-VIE, and fine-tuned models at https://huggingface.co/fairme/Qwen2.5-VL-7B-SFT.

cs.CV↗

arXiv2026

NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) significantly enhances the ability of Large Language Models (LLMs) to provide accurate and contextually relevant answers by dynamically integrating external databases. However, traditional RAG methods are primarily constrained by their reliance on text-based retrieval strategies, which often struggle with complex questions requiring multi-hop reasoning. To address this limitation, we introduce Neural Graph Matching based Retrieval-Augmented Generation (NGM-RAG), a novel framework that leverages graph structures to effectively capture and utilize relational knowledge for improved retrieval and answer generation. NGM-RAG explicitly incorporates graph construction, graph matching, and answer generation into a unified process. Within this framework, we propose a neural graph matching approach that combines text-based matching with Graph Neural Networks (GNNs). By employing an adaptive weighting strategy, NGM-RAG efficiently integrates multiple matching methods to select the most relevant contextual node information for answer generation. Experimental results on multi-hop question answering and long-context summarization tasks demonstrate that our NGM-RAG model achieves superior performance compared to both traditional NaiveRAG methods and state-of-the-art graph-enhanced approaches such as GraphRAG and LightRAG.

cs.IR↗

arXiv2026

RED-SEGA:Resilient Decentralized Stochastic Proximal Optimization with Gradient Sketching over Time-Varying Networks

Variance reduction is indispensable in Byzantine-resilient decentralized stochastic optimization over multi-agent systems (MASs) for its ability to mitigate gradient noise and thereby enhance the resilient aggregation process. However, most existing Byzantine-resilient decentralized variance-reduced (VR) stochastic gradient algorithms rely on random data sampling, which proves inefficient in data-scarce yet high-dimensional tasks, for instance, image deblurring. This paper pursues an alternative technical line that achieves variance reduction via gradient sketching. To this end, we first formulate a class of structural risk minimization (SRM) problems, where the local objectives are not necessarily decomposable and their gradients may be unavailable. To solve the SRM problems in a decentralized manner, we integrate a gradient-sketching technique into decentralized stochastic proximal gradient descent with gossip communication to propose a decentralized VR stochastic gradient algorithm, dubbed Gossip-SEGA.Since Gossip-SEGA does not provide any resilience against Byzantine attacks, a resilient extension of Gossip-SEGA,namely RED-SEGA,is developed via replacing the weighted average in Gossip-SEGA by a norm-penalized approximation. Theoretically, we derive sufficient conditions for both consensus (among reliable agents) and linear convergence rate of RED-SEGA over time-varying networks. The effectiveness and resilience of the proposed algorithms are validated through numerical experiments.

math.OC↗

arXiv2026

TactiDex: A Real-World Tactile-Guided Benchmark for Human-Like Dexterous Manipulation

Tactile feedback is fundamental to Hand-Object Interaction (HOI), governing contact formation, force regulation, and stable manipulation, making it essential for achieving true human-like dexterous manipulation. Yet, current human-to-robot dexterous transfer pipelines primarily rely on kinematic trajectories, resulting in motion imitation without physically grounded interaction. To address this, we introduce TactiDex, a real-world tactile-guided benchmark specifically designed to move dexterous manipulation beyond kinematic mimicry toward contact-level human-likeness. TactiDex provides a comprehensive dataset that elegantly aligns whole-hand tactile signals with multi-granularity kinematic and object states, coupled with standardized evaluation metrics. Building upon this data paradigm, we propose a tactile-driven transfer framework that effectively translates human demonstrations into physically plausible robotic execution. We introduce TactiSkill, a framework built upon a novel tri-component tactile reward that innovatively uses tactile signals as structured supervision. This reward unifies guidance, human-like alignment, and contact constraints into a single objective. Through comprehensive experiments on both single and bimanual tasks, we demonstrate that TactiSkill achieves superior performance in manipulation success and physical realism. This work lays a crucial foundation for advancing tactile-aware dexterous manipulation. Our project page at https://tactidex.github.io/.

cs.RO↗

arXiv2026

A Blockchain Consensus Mechanism for Distributed Electricity Trading

Distributed power systems complement centralized grids by coordinating distributed energy resources (DERs) to achieve regional energy self-sufficiency. Scaling such systems raises four persistent challenges: decentralized coordination, fair economic settlement, trustworthy operation, and system optimization, all without a central authority. This paper proposes Proof of Energy (PoE), a blockchain consensus mechanism that addresses these challenges through cryptographically secured, contribution-proportional node selection. In PoE, block generation rights are tied directly to real-world energy contributions, enabling distributed consensus without centralized dispatch. An Energy Contribution Unit (ECU) model is introduced to map heterogeneous energy services onto a unified value metric via scarcity-weighted normalization. A Verifiable Random Function (VRF)-based proposal mechanism then ensures selection probability is strictly proportional to node contribution, preserving fairness and resisting manipulation. Case studies validate PoE across three dimensions: grid coordination, incentive fairness, and optimization efficiency. The result is a cryptographically secured, incentive-compatible framework for decentralized value distribution in energy systems.

cs.CR↗

arXiv2026

The capability of CSST in characterizing planetary atmospheres. I. transmission spectroscopy of hot Jupiters

Transmission spectroscopy has become a primary tool for probing exoplanetary atmospheres, enabling constraints on their chemical compositions and providing limited information on their thermal properties. We assess the potential of the upcoming Chinese Space Station Telescope (CSST) for exoplanet atmospheric characterization through transmission spectroscopy. Theoretical spectra of hot gas planets are generated and used to simulate slitless spectroscopic observations with the CSST across the ultraviolet-to-near-infrared range. Atmospheric retrievals performed on the simulated data are compared with the input models to assess the robustness and accuracy of parameter determinations. We find that multi-band observations across three wavelength channels, each with two transits can place meaningful constraints on key atmospheric parameters. For multi-band observations that account for correlated (red) noise, future CSST observations are expected to achieve constraints that are comparable to, or in some cases slightly weaker than, those of the Hubble Space Telescope (HST), depending on the noise level and observing strategy. We conclude that CSST will provide unique and complementary constraints on the chemical compositions and physical properties of exoplanetary atmospheres, particularly for atomic species, metal-bearing molecules, and scattering processes accessible in the UV and optical, thereby complementing JWST's infrared sensitivity to molecular species.

astro-ph.EP↗

arXiv2026

Detection of CO, H$_2$O, and OH in WASP-18b with JWST/NIRISS using Direct-Extracted Spectra and Cross-Correlation

The James Webb Space Telescope (JWST) has revolutionized the characterization of exoplanetary atmospheres, offering unprecedented sensitivity to probe their chemical and physical properties. Recently, a growing trend has emerged to obtain atmospheric information directly from pixel-level planetary spectra. In this work, we re-analyzed the WASP-18b NIRISS/SOSS dataset by employing a direct extraction method. This new method preserves the spectral information at the native instrumental resolution, thereby enabling the application of cross-correlation techniques and providing atmospheric retrievals with enhanced precision and richer information content. With this methodology, we report detections of CO at $4.4\sigma$ significance, H$_2$O at $3.4\sigma$, and OH at $7.8\sigma$, where CO and OH were previously unseen. Building on these unambiguous detections, our subsequent retrieval analysis significantly improves the constraints on atmospheric abundances. Our results demonstrate that the cross-correlation technique effectively extracts molecular signals from medium-resolution JWST data, enhancing detection sensitivity. By revisiting JWST archival data with cross-correlation and retrieval analysis, we can achieve a more comprehensive survey of planetary atmospheric chemistry, thereby placing precise constraints on key parameters such as planetary metallicity and C/O ratio.

astro-ph.EP↗

arXiv2026

Optical transmission spectrum of HAT-P-47b: evidence for aerosols and tentative TiO absorption

Transmission spectroscopy enables the characterization of exoplanet atmospheres by probing absorption features in their terminator regions. In the optical, it is particularly sensitive to metal oxides and atomic species that can strongly influence atmospheric energy balance and thermal structure. We aim to investigate the atmospheric properties of the hot Jupiter HAT-P-47b through optical transmission spectroscopy. Thirteen TESS transits were analyzed to refine the planetary ephemeris and system parameters. Two ground-based transits were observed with LBT/MODS and GTC/OSIRIS+. Chromatic transit light curves were modeled to derive instrument-specific transmission spectra and multiple Bayesian spectral retrievals were performed to characterize the atmospheric properties. The MODS transmission spectrum provides moderate Bayesian evidence ($\Delta\ln\mathcal{Z}=2.68$) for TiO absorption, whereas the OSIRIS+ spectrum does not yield statistically significant evidence for any specific opacity source. Both datasets exhibit a wavelength-dependent slope indicative of enhanced aerosol scattering. The MODS and OSIRIS+ joint free-chemistry retrieval, dominated by the higher signal-to-noise MODS data, yields moderate evidence ($\Delta\ln\mathcal{Z}=3.44$) for TiO with a log mass fraction of $-6.86^{+0.64}_{-0.63}$ dex. The same model indicates an aerosol contribution to the optical scattering opacity approximately $5000\times$ larger than pure H$_2$ Rayleigh scattering. HAT-P-47b appears to host a cloudy atmosphere with evidence for aerosols and tentative evidence for TiO absorption. Future high-precision observations will be essential to confirm the presence of TiO and further characterize its atmospheric structure.

astro-ph.EP↗

arXiv2026

The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates

With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-token prediction and often fail to follow instructions or produce well-formed answers under standard prompting and direct decoding. As a result, benchmark performance can conflate model capability with decoding-induced failures to produce task-oriented outputs, while exposing such behavior often relies on costly post-training. Recent decodingonly approaches attempt to reshape output distributions, but such methods can be inefficient and brittle across open-ended tasks. To address these limitations, we propose Energy-Based Decoding (EBD), a training-free, reward-guided framework for activating task-oriented behaviors from frozen pre-trained LLMs across both open-ended and objective tasks. EBD augments decoding with an external lightweight reward model, steering generations toward high-utility responses while anchoring them to the pre-trained model prior through a reward-tilted target distribution. We show that EBD shifts base-model outputs toward more instructionfollowing behavior, increasing behavioral similarity to post-trained counterparts and enabling a fairer inference-time evaluation of accessible pre-trained-model behavior. Empirically, EBD outperforms baselines across five models and six benchmarks, improving Qwen3-8B-Base on AlpacaEval2.0 from 8.8 to 44.5, reducing Mistral-7B Math500 latency by 18.9x relative to prior decoding work, and remaining robust to reward-model size.

cs.CL↗

arXiv2026

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single step, LocateAnything preserves intra-box geometric coherence and unlocks substantial parallelism. We show that PBD improves both decoding throughput and localization accuracy. We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples, substantially increasing data diversity for high-precision localization. Extensive evaluations show that LocateAnything advances the speed-accuracy frontier, achieving significantly higher decoding throughput while improving high-IoU localization quality across diverse benchmarks. The results highlight the complementary benefits of Parallel Box Decoding and large-scale training data in enabling efficient and precise unified visual grounding and detection.

cs.CV↗

arXiv2026

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

cs.LG↗

arXiv2026

Optimal Decentralized Dynamic Energy Management over Asynchronous Peer-to-Peer Transactive Networks via Operator Splitting

Peer-to-peer (P2P) energy management facilitates decentralized resource allocation among prosumers, improving local hosting capacity for renewables and minimizing energy expenditures while ensuring data privacy through distributed coordination. However, conventional P2P energy management methods are confined to synchronous scheduling paradigms, creating synchronization bottlenecks that fundamentally conflict with the dynamic and decentralized nature of P2P energy management tasks. To bridge this gap, this paper focuses on resolving a class of dynamic energy management problems over asynchronous P2P (Asyn-P2P) transactive networks. We first recast the dynamic energy management problems into a saddle-point problem, and then propose a synchronous decentralized dynamic energy management algorithm, dubbed Syn-DYNA,based on operator splitting theory. To eliminate the global synchronization clock in Syn-DYNA, we introduce a random activation scheme, together with local buffers for latest state tracking, to develop an asynchronous variant of Syn-DYNA, namely Asyn-DYNA. Based on monotone operator theory, theoretical analysis proves a non-asymptotic linear convergence rate for Syn-DYNA and establishes the almost sure convergence ofAsyn-DYNA. Numerical experiments validate effectiveness of Syn-DYNA and Asyn-DYNA algorithms by tackling a dynamic energy management task over P2P transactive networks.

eess.SY↗

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

Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index structures to select relevant tokens, and on complex quantization schemes to reduce memory usage. This fragmented design introduces redundant overhead and limits scalability. In this paper, we propose a novel paradigm: treating the compressed key representation not merely as storage, but as a self-indexing structure that directly enables efficient sparse attention. By designing a sign-based 1-bit vector quantization (VQ) scheme, our method unifies compression and retrieval in a single, hardware-friendly format. This approach eliminates the need for external indices or learning-based predictors, offering a lightweight yet robust solution for memory-constrained inference. All components are designed to be hardware-efficient and easy to implement. By implementing custom CUDA kernels, our method integrates seamlessly with FlashAttention, minimizing additional runtime and memory overhead. Experimental results demonstrate that our approach delivers both effectiveness and efficiency.

cs.LG↗