Searcharxiv⌕ Search

arXiv subjects

Yijia Zhang

Publications and source records attributed to Yijia Zhang.

At least 19 recordsLinked to original sources

TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning

Test-time reinforcement learning enables language models to adapt using rewards derived from their own answers. However, majority voting can reinforce incorrect solutions even when correct alternatives are available. Our training audit shows that false positives (incorrect responses receiving positive rewards) dominate reward errors. We focus on a practical regime where ground-truth rewards are difficult to obtain at scale, while a limited labeled source set is available. We introduce TRUER, a framework that uses limited supervision to train a reward rectifier that distinguishes correctness from consensus. To achieve this goal, we train the rectifier with an emphasis on incorrect majorities and correct minorities, targeting cases where consensus and correctness disagree. After that, we freeze the rectifier and use it to correct rewards during subsequent test-time adaptation. By improving reward accuracy and thereby model performance, TRUER consistently outperforms naive TTRL in both metrics across all evaluated configurations.

cs.LG↗

Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method

Instruction tuning has become a common paradigm for applying large language models (LLMs) to biomedical named entity recognition (BioNER). However, existing instruction-tuning approaches still face two key challenges. First, conventional natural-language instructions typically serialize BioNER annotations as flat textual outputs, providing limited structural constraints for typed entity extraction. Second, high-quality biomedical annotations are limited, and learning from a single serialized output form may restrict structural diversity and reduce model robustness. Although external biomedical knowledge can be introduced to alleviate data scarcity, it often requires costly resource construction. To address these challenges, we propose MITE, a Multiple Programming Languages Instruction Tuning and Ensemble method for BioNER. MITE reformulates BioNER as a structure-to-structure generation task by representing both instructions and entity outputs in code-formatted representations. Specifically, each training instance is transformed into multiple programming-language formats, including Python, C++, and Java, while preserving the same underlying entity semantics. These language-specific representations provide structurally diverse supervision without requiring external biomedical knowledge or additional annotations. During inference, MITE aggregates predictions from different code formats through an entity-level voting strategy, reducing language-specific prediction variance and improving robustness. Experiments on three widely used BioNER datasets demonstrate that MITE achieves competitive performance against representative BERT-based and LLM-based baselines, attaining the best results on two benchmarks. Ablation studies further validate the effectiveness of multi-language representations.

cs.CL↗

Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs

Stance detection requires identifying an author's attitude toward a given target, sometimes based on conversational context. Jev, a specialized decision model designed for structured decision-making, offers an alternative to general-purpose large language models (LLMs). In this work, we evaluate Jev on two stance detection datasets, VAST (English texts) and ZS-CSD (Chinese conversations), comparing it with four general-purpose LLMs and two fine-tuned models. Results show that Jev achieves competitive performance on VAST, matching GPT-5.6 and outperforming the other general-purpose LLMs. However, it falls behind stronger LLMs on ZS-CSD, particularly in distinguishing favor from against. Further analysis suggests that this limitation may be related to understanding reply relationships and stance direction rather than conversation length alone. These findings highlight both the potential and limitations of Jev for stance detection.

cs.CL↗

Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks

Jev is a "System One" model that returns a choice among given options instead of generating text. We study how such a specialized decision model compares with general-purpose large language models (LLMs). We evaluate Jev on 13 multiple-choice benchmarks covering knowledge, reasoning, and multilingual understanding, and compare it with 19 LLMs in three tiers: frontier, representative, and small. Jev is competitive with frontier LLMs on knowledge and commonsense benchmarks and obtains the best score on MMLU-Redux and ARC-Challenge. Outside mathematics, it also outperforms most representative LLMs and all small LLMs. However, it falls behind on mathematical word problems: on MathQA, it is 17.7 points below the frontier median and scores lower than all 19 LLMs. These results indicate that a specialized decision model can match general-purpose LLMs on decisions that rely mainly on knowledge, but not on decisions that require multi-step calculation.

cs.CL↗

Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation

While hypergraph-based Retrieval-Augmented Generation (RAG) effectively captures higher-order multi-entity correlations, existing paradigms treat extracted hyperedges as isolated factual assertions. This structural fragmentation engenders rigid "knowledge islands" that bottleneck multi-hop causal inference, temporal tracking, and narrative synthesis. To systematically address these challenges, we introduce Dual-Hypergraph Indexing (DHI), a hierarchical representation framework that elevates discrete facts into structured analytical insights. DHI couples a foundational entity-relation factual hypergraph ($H_K$) with an elevated deep-insight hypergraph ($H_D$) via a dual-pathway aggregation algorithm. Specifically, DHI employs: (1) importance-driven hub aggregation via 5-metric topological profiling and adaptive thresholding to capture spatial semantic clusters; and (2) temporal chunk-chain progressive aggregation via sliding-window greedy exploration to track chronological evolutions. Across five benchmarks, DHI achieves state-of-the-art performance, boosting logical coherence by +1.53 on the multidisciplinary Mix benchmark and scoring 85.78\% on complex medical pathology reasoning tasks. DHI provides a robust architecture for next-generation multi-hop RAG.

cs.IR↗

Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG

While graph-based and hypergraph-based Retrieval-Augmented Generation (RAG) significantly mitigate hallucinations in Large Language Models (LLMs), existing structure-based RAG systems typically adopt static traversal strategies regardless of the query complexity. We identify this ``static retrieval fallacy'' as a primary source of computational redundancy for simple queries and cognitive context gaps for complex reasoning tasks. To balance reasoning quality and inference efficiency, we propose Asymmetric Dynamic Routing (ADR), an intent-conditioned retrieval framework operating over hierarchical knowledge graphs. ADR employs a lightweight structured classifier to dynamically dispatch queries among three asymmetric topological traversal operators: localized fact anchoring, bottom-up adjacency diffusion, and top-down insight grounding, which collectively enable bidirectional information flow across hierarchical knowledge layers. Extensive empirical evaluations across five domain-specific corpora demonstrate that ADR maintains strong reasoning performance while reducing prompt token consumption by up to 48.7\% and end-to-end query latency by 45.3\%, yielding a favorable quality--efficiency trade-off for query-adaptive Hypergraph RAG.

cs.IR↗

What Happens During Autonomous Deep Research After the User Steps Away?

In autonomous deep research, a user provides a task and relevant background, then leaves the agent to conduct an extended investigation without further human intervention. We study how this initial user information is reflected in intermediate actions and how these actions relate to final recommendations. We introduce DRaligned, a counterfactual behavioral evaluation framework built on PDR-Bench. By varying one task-relevant user factor while keeping the remaining context fixed, we compare acquisition requests, working drafts, and final reports. Source-grounded extraction, blinded local judgments, and deterministic aggregation yield coarse directional measurements while leaving ambiguous cases unresolved. Our experiments show that strong user-specific delivery can emerge from a largely shared research process: agents investigate similar broad questions but allocate requests differently, and final recommendations distinguish user conditions more clearly than explicit requests do. Reports can also integrate user factors that were not jointly visible during acquisition. In readable draft-to-report comparisons, recommendations often retain their coarse user-specific direction despite substantial rewriting. Final directional differences recur across tested agent models, execution harnesses, and evaluator models, even as execution paths vary. These findings describe how initial user information shapes autonomous research and clarify the relationship between the process an agent follows and the recommendations it delivers.

cs.AI↗

EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models

Large Language Models (LLMs) have been used in various industries. However, ensuring their compliance with complex laws and regulatory frameworks remains a great challenge. Existing evaluation paradigms mainly rely on static benchmarks that suffer from three severe limitations: First, the compliance rules being used do not comply with the requirements of Artificial Intelligence (AI) laws and regulations; Second, they only handle apparent, explicit compliance risks, leaving implicit and covert compliance risks undetected; Third, they fail to track the systematic propagation of risks along logical dependency chains or evaluate compliance within nuanced, context-based real-world scenarios. To bridge this critical gap, we introduce EADC, a novel advanced evaluation benchmark of LLMs based on an AI compliance knowledge graph and AI compliance legal experts. By mapping abstract legal rules into structured logical multi-relational graphs, our framework enables automated, evolving agents to distill and synthesize highly sophisticated adversarial scenarios. This compliance benchmark is reviewed and corrected by human AI legal experts throughout the whole process. The resulting dataset (4,435+ QA pairs) provides an extensive, multi-dimensional taxonomy covering critical regulatory frontiers, including bias and discrimination, fairness, personal privacy protection, and values. Crucially, our compliance dataset moves beyond shallow string-matching by incorporating contextual long-horizon interactions and logic-driven hazard chains, capturing deeply embedded compliance anomalies that bypass traditional filters. Experiment evaluations demonstrate that our framework exposes critical regulatory blind spots in state-of-the-art LLMs, offering a rigorous, AI laws and regulations-aligned benchmark to safeguard high-level and deep compliance in the application of LLMs.

cs.AI↗

SN 2025fhm: A central-engine powered Ic-BL supernova associated with X-ray transient EP250304a

We present X-ray, optical, and radio follow-up observations of EP250304a, an extragalactic fast X-ray transient (EFXT) discovered by the Einstein Probe. Its X-ray light curve exhibits two broad pulses with comparable peak fluxes within the first $\sim$1~ks, a feature rarely seen among low-luminosity gamma-ray bursts or EFXTs. Optical follow-up observations were carried out using the Korea Microlensing Telescope Network, the Thai Robotic Telescope, the Las Cumbres Observatory 1~m global network, the Gemini Multi-Object Spectrograph on Gemini south telescope, and the Global Supernova Network. The fast-cooling phase (within 3 days) of optical data can be well fitted by a shocked cocoon model. However, during the supernova phase (SN 2025fhm, from 3 to 88 days), the late-time light curve cannot be explained solely by radioactive $^{56}$Ni decay, as demonstrated by a grid of simulations using the one-dimensional Lagrangian radiation hydrodynamics code SNEC, which reveals a significant energy excess at late epochs. To account for this excess, a central engine like a rapidly spinning, highly magnetized neutron star is needed to provide additional energy injection. This model yields a best-fit spin period of $\sim$12.60~ms and magnetic field strength of $\sim 3.52\times10^{15} \rm G$, and it successfully explains both the late-time bolometric light curve and the early X-ray pulse structures. Our results indicate that EP250304a/SN 2025fhm is likely powered by a central magnetar rather than by radioactive decay alone, offering new insights into the energy budget and physical origin of EFXTs and their associated supernovae.

astro-ph.HE↗

On the Brunn-Minkowski inequality for $q$-th dual quermassintegrals with $q>n$

In this paper, we study the Brunn-Minkowski inequality for $q$-th dual quermassintegrals with $q>n$. This problem was recently posed by Sadovsky and Zhang. First, by a second variation argument and a dimension reduction construction, we show that the inequality fails for arbitrary convex bodies when $q>n$, and fails even in the origin-symmetric class when $q>n+2$. Secondly, we prove the endpoint case $q=n+2$ for origin-symmetric convex bodies via Hadwiger's inequality for the polar moment of inertia. Finally, for unconditional convex bodies, we establish the inequality in the full range $0<q\le n+1$ by using a singular weighted Reilly formula and a coordinate-slice Hardy inequality. As applications, we derive several uniqueness results for the corresponding dual curvature measures.

math.DG↗

RhinoVLA Technical Report

Vision-Language-Action (VLA) models have shown strong potential for robotic manipulation, but real-time deployment on edge hardware remains challenging. In this work, we identify VLM visual and context tokens as a major source of deployment latency: for GEMM-dominated projection operators, computation grows linearly with the number of input tokens when model dimensions are fixed. Motivated by this observation, we propose RhinoVLA, a deployment-oriented VLA model co-designed with the Huixi R1 edge SoC. RhinoVLA adopts a token-efficient Qwen3-VL backbone and a continuous Action Expert, reducing the VLM-side token and computation burden while preserving pretrained multimodal capability. To support cross-robot learning, RhinoVLA further introduces a unified interface that combines View Registry, 72D physical state-action slot space, and robotinstance LoRA, allowing heterogeneous robot observations and action schemas to be aligned under a shared policy. On the deployment side, RhinoVLA is optimized through hardware-aware compilation, mixed-precision execution, and parallel visual encoding. Experiments show that RhinoVLA achieves downstream performance comparable to π0.5 at a similar parameter scale, while reaching 11.69 Hz end-to-end inference on Huixi R1, meeting the 10 Hz real-time closedloop control target. The project will be open-sourced at https://github.com/HuixiAI/RhinoVLA.

cs.RO↗

Pinching Antenna-Assisted ISAC with Waveguide Mode Selection

Conventional pinching antenna (PA)-assisted integrated sensing and communication (ISAC) architectures typically assume static receiver locations or predetermined receive waveguides, thereby underutilizing the inherent spatial degrees of freedom. This paper proposes a novel mode-selectable PA-assisted ISAC framework to maximize the post-combining sensing signal-to-noise ratio while satisfying multi-user quality-of-service constraints by jointly optimizing the waveguide mode selection, transmit beamforming, and transmit/receive PA positions. To tackle the resulting mixed-integer nonconvex optimization problem, we develop a low-complexity block-coordinate descent algorithm that leverages a penalty-based majorization-minimization method to achieve high-quality suboptimal solutions. Numerical results demonstrate that the proposed design significantly outperforms both traditional PA and fixed-antenna benchmarks by synergistically harnessing spatial adaptability and modal reconfigurability. In particular, the mode-selectable design enables the coordinated optimization of transmit/receive operations and sensing-communication resource allocation, thereby maintaining sensing robustness under stringent communication requirements.

eess.SP↗

HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation

Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real-world HSIs suffer from noise, blur, and resolution loss. However, existing models trained on source data often fail on target domains lacking clean references, a common real-world scenario. To address this, we present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances HSI restoration by augmenting limited training images with synthetic data matching the target distribution, without extra clean target-domain HSI data. It has three stages: (i) proxy generation, where off-the-shelf restoration models are applied to degraded target observations to produce semantics-preserving proxy HSIs that approximate clean target-domain images; (ii) distribution-adaptive synthesis, where a blur-robust unCLIP diffusion model generates target-aligned RGBs from proxy RGBs with prompt conditioning and embedding-space noise initialization. The warp-based spectral transfer module then synthesizes HSIs by aligning each generated RGB with its proxy RGB, estimating soft patch-wise transport weights, and applying these weights and learnable local interpolation kernels to the proxy HSI; and (iii) aligned supervised finetuning, where restoration networks pretrained on the source distribution are finetuned with proxy HSIs and synthesized target-aligned HSIs, then deployed on degraded target images. We also provide theoretical analysis showing that, under stated assumptions, the proposed augmentation-based finetuning obtains a tighter target-domain restoration-risk upper bound by jointly improving target-distribution coverage and controlling spectral bias. Experiments on simulated and real datasets across denoising, super-resolution, and other restoration tasks demonstrate that HIR-ALIGN is superior to proxy-only target-adaptation baselines and outperforms representative unsupervised methods in most cases.

cs.CV↗

Scalable Peptide Design via Memory-Efficient Equivariant Transformer

Target-specific peptide design requires sequence and structure co-design under full atom geometric constraints. Latent generative frameworks offer an effective route for this problem by compressing fine grained atomic structures into block level latent representations and performing conditional generation in a compact latent space. However, the scalability of such systems depends heavily on the geometric backbone used throughout their encoding, decoding, and denoising components. We introduce MEET (Memory Efficient Equivariant Transformer), an E(3) equivariant backbone for scalable atomistic peptide modeling. MEET maintains coupled invariant scalar and equivariant vector feature streams, while reformulating geometric computation around memory efficient attention. It initializes vector features through global coordinate aggregation, incorporates pairwise distances through augmented query and key dot products, and injects covalent bond information through sparse bond adaptation. Integrated into a VAE and latent diffusion pipeline for full atom peptide generation, MEET achieves linear memory scaling with atom count and improves generation quality over existing peptide design methods. Experiments on large scale AFDB derived datasets further show that the proposed backbone supports systematic model and data scaling, leading to better binding affinity, physical validity, and sample diversity.

cs.LG↗

STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction

Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the distribution of action sequences and capture multimodality. However, iterative denoising leads to substantial inference latency, limiting control frequency in real-time closed-loop systems. Existing acceleration methods either reduce sampling steps, bypass diffusion through direct prediction, or reuse past actions, but often struggle to jointly preserve action quality and achieve consistently low latency. In this work, we propose STEP, a lightweight spatiotemporal consistency prediction mechanism to construct high-quality warm-start actions that are both distributionally close to the target action and temporally consistent, without compromising the generative capability of the original diffusion policy. Then, we propose a velocity-aware perturbation injection mechanism that adaptively modulates actuation excitation based on temporal action variation to prevent execution stall especially for real-world tasks. We further provide a theoretical analysis showing that the proposed prediction induces a locally contractive mapping, ensuring convergence of action errors during diffusion refinement. We conduct extensive evaluations on nine simulated benchmarks and two real-world tasks. Notably, STEP with 2 steps can achieve an average 21.6% and 27.5% higher success rate than BRIDGER and DDIM on the RoboMimic benchmark and real-world tasks, respectively. These results demonstrate that STEP consistently advances the Pareto frontier of inference latency and success rate over existing methods.The code is publicly available at https://github.com/Kimho666/STEP.

cs.RO↗

Deep VLBI constraints on compact radio cores in four ultraluminous X-ray sources

We present high-sensitivity Very Long Baseline Interferometry (VLBI) observations of four ultraluminous X-ray sources (ULXs): Holmberg II X-1, IC 342 X-1, NGC 6946 X-1, and NGC 925 X-1. No compact emission was detected on milliarcsecond scales, with rms noise levels reaching approximately 5--20 $μ$Jy. The corresponding $5σ$ flux density upper limits reach $\sim 26\,μ\mathrm{Jy}$, implying radio luminosity limits $L_{\rm R} \lesssim 2 \times 10^{33}\,\mathrm{erg\,s^{-1}}$. This disfavors any persistently bright hard-state-like compact core at our sensitivity level. The previously reported VLBI core in Holmberg II X-1 exhibits significant long-term variability, broadly consistent with an overall decline over the past decades. This behavior is consistent with emission from optically-thin ejecta undergoing adiabatic expansion. The VLBI non-detections may reflect intrinsically weak/intermittent compact emission, and/or low--surface--brightness structure that is resolved out by VLBI, and/or absorption/propagation effects such as free--free absorption in dense, ionized winds.

astro-ph.HE↗

E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition

Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground each entity to a corresponding visual region in an associated image. Existing approaches predominantly adopt pipeline-based architectures that decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization. In this paper, we propose E2E-GMNER, a fully end-to-end generative framework that unifies entity recognition, semantic typing, visual grounding, and implicit knowledge reasoning within a single multimodal large language model. We formulate GMNER as an instruction-tuned conditional generation task and incorporate chain-of-thought reasoning to enable the model to adaptively determine when visual evidence or background knowledge is informative, reducing reliance on noisy cues. To further address the instability of generative bounding box prediction, we introduce Gaussian Risk-Aware Box Perturbation (GRBP), which replaces hard box supervision with probabilistically perturbed soft targets to improve robustness against annotation noise and discretization errors. Extensive experiments on the Twitter-GMNER and Twitter-FMNERG benchmarks demonstrate that E2E-GMNER achieves highly competitive performance compared with state of the art methods, validating the effectiveness of unified end-to-end optimization and noise-aware grounding supervision. Code is available at:https://github.com/Finch-coder/E2E-GMNER

cs.CV↗

SMC-AI: Scaling Monte Carlo Simulation to Four Trillion Atoms with AI Accelerators

The rapid advancement of deep learning is reshaping the hardware design landscape toward AI tasks, posing fundamental challenges for HPC workloads such as atomistic simulation. Here we present SMC-AI, a general algorithmic framework that extends the SMC-X method for efficient canonical Monte Carlo simulation on AI accelerators, including GPUs and NPUs, while maintaining extreme scalability. The implementation of SMC-AI on an NPU cluster reaches unprecedented performance, achieving MC simulation of 4 trillion atoms on 4096 NPU dies. This represents the largest ML-accelerated atomistic simulation reported, delivering 32X system size and 1.3X throughput than previous records, with a relatively small computational budget. Excellent strong and weak scaling efficiency are reached for both the NPU and GPU implementation. By decoupling ML models from simulation, SMC-AI creates an abstraction that facilitates integration and porting of diverse ML models, laying a foundation for the future development of scalable scientific software.

physics.comp-ph↗