arXiv subjects

Yang Xu

Publications and source records attributed to Yang Xu.

At least 91 records · Page 5Linked to original sources

arXiv2026

Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices

In agent-driven question answering (QA) applications, retrieval-augmented generation (RAG) is commonly introduced to enhance the response accuracy of large language models (LLMs) by providing additional context. Due to the inherent noise in retrieval results and the coarse granularity of document-level retrieval, the retrieved context often contains substantial redundant information. In this setting, the agent prompt, consisting of the user query and the associated retrieved context, leads to unnecessary computational overhead during LLM inference. Existing prompt compression methods typically rely on auxiliary small language models (SLMs) to estimate context importance. However, such approaches introduce significant memory and computational overhead, which limits their deployment on resource-constrained edge devices. In this paper, we propose CORE, a two-stage sentence-level prompt compression method that eliminates the need for SLMs. In the first stage, CORE constructs an answer set via named entity recognition (NER) and a clue set via semantic matching. In the second stage, CORE refines the clue set using an orthogonal residual retrieval strategy and designs a spatial proximity-based metric to filter the answer set. The two sets are then combined to form the final compressed context. We implement CORE on an NVIDIA Jetson AGX Orin edge device and a Huawei Nova smartphone. Experimental results demonstrate that within a 2000-token budget, CORE improves accuracy by at least 30.19% compared to state-of-the-art baselines, while reducing memory usage by at least 50.47% and achieving at least 1.94 times speedup on the edge device. Moreover, compared to the state-of-the-art LLMLingua2 method, CORE achieves a substantial energy reduction of 95.74% on the smartphone, highlighting its practicality and generalizability for mobile deployments.

cs.CL↗

arXiv2026

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models

Backchannels and fillers are important linguistic expressions in dialogue, but often treated as 'noise' to be bypassed in modern transformer-based language models (LMs). Here, we study how they are represented in LMs using three fine-tuning strategies on three dialogue corpora in English and Japanese, in which backchannels and fillers are both preserved and annotated. This allows us to investigate how fine-tuning can help LMs learn these representations. We first apply clustering analysis to the learnt representation of backchannels and fillers, and find increased silhouette scores in representations from fine-tuned models, which suggests that fine-tuning enables LMs to distinguish the nuanced semantic variation in different backchannel and filler use. We also employ natural language generation metrics and qualitative analyses to verify that utterances produced by fine-tuned LMs resemble those produced by humans more closely. Our findings suggest the potential for transforming general LMs into conversational LMs that can produce human-like language more adequately.

cs.CL↗

arXiv2026

Identifying the Periodicity of Information in Natural Language

Recent theoretical advancement of information density in natural language has brought the following question on desk: To what degree does natural language exhibit periodicity pattern in its encoded information? We address this question by introducing a new method called AutoPeriod of Surprisal (APS). APS adopts a canonical periodicity detection algorithm and is able to identify any significant periods that exist in the surprisal sequence of a single document. By applying the algorithm to a set of corpora, we have obtained the following interesting results: Firstly, a considerable proportion of human language demonstrates a strong pattern of periodicity in information; Secondly, new periods that are outside the distributions of typical structural units in text (e.g., sentence boundaries, elementary discourse units, etc.) are found and further confirmed via harmonic regression modeling. We conclude that the periodicity of information in language is a joint outcome from both structured factors and other driving factors that take effect at longer distances. The advantages of our periodicity detection method and its potentials in LLM-generation detection are further discussed.

cs.CL↗

arXiv2026

Online Survival Analysis: A Bandit Approach under Cox PH Model

Survival analysis is a widely used statistical framework for modeling time-to-event data under censoring. Classical methods, such as the Cox proportional hazards (Cox PH) model, offer a semiparametric approach to estimating the effects of covariates on the hazard function. Despite its importance, survival analysis has been largely unexplored in online settings, particularly within the bandit framework, where decisions must be made sequentially to optimize treatments as new data arrive over time. In this work, we take an initial step toward integrating survival analysis into a purely online learning setting under the Cox PH model, addressing key challenges including staggered entry, delayed feedback, and right censoring. We adapt three canonical bandit algorithms to balance exploration and exploitation, with theoretical guarantees of sublinear regret bounds. Extensive simulations and semi-real experiments using SEER cancer data demonstrate that our approach enables rapid and effective learning of near-optimal treatment policies.

stat.ML↗

arXiv2026

Self-focusing of high-intensity beams with grid structures

Laser beams with high optical power propagating in a Kerr medium can undergo self-focusing when their power exceeds a critical power determined by the optical properties of the medium. The highly concentrated energy close to the in the region of the self-focus can lead to other nonlinear phenomena and cause significant irreversible damage to the material. We propose a transverse grid beam structure that effectively suppresses self-focusing even in the absence of other competing effects through the redistribution of optical power by inter-beamlet nonlinear interaction. We find that a beam with a $N \times N$ grid structure with optimized lattice spacing undergoes a dimension-dependent multi-stage self-focusing. We also identify specific grid layouts that can increase the total transmitted power beyond that permitted by the critical level of self-focusing for each beamlet. Lastly, we derive a general numerical relation between the optimal grid lattice spacing and the size of beamlets. Our results could potentially inform the use of beam shaping to prevent damage to optical components in high-powered and directed-energy applications.

physics.optics↗

arXiv2026

Evaluating Memory Capability in Continuous Lifelog Scenario

Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on online one-on-one chatting or human-AI interactions, thus neglecting the unique demands of real-world scenarios. Given the scarcity of public lifelogging audio datasets, we propose a hierarchical synthesis framework to curate \textbf{\textsc{LifeDialBench}}, a novel benchmark comprising two complementary subsets: \textbf{EgoMem}, built on real-world egocentric videos, and \textbf{LifeMem}, constructed using simulated virtual community. Crucially, to address the issue of temporal leakage in traditional offline settings, we propose an \textbf{Online Evaluation} protocol that strictly adheres to temporal causality, ensuring systems are evaluated in a realistic streaming fashion. Our experimental results reveal a counterintuitive finding: current sophisticated memory systems fail to outperform a simple RAG-based baseline. This highlights the detrimental impact of over-designed structures and lossy compression in current approaches, emphasizing the necessity of high-fidelity context preservation for lifelog scenarios.

cs.CL↗

arXiv2026

Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent sentence-level structure of natural language. This is a critical oversight, as LLMs acquire linguistic capabilities through exposure to human-generated texts, which are inherently structured at the sentence level. Motivated by this gap, we propose an approach that inserts delimiters at sentence boundaries in LLM inputs, which not only integrates dummy tokens into the context, but also facilitates LLMs with sentence-by-sentence processing behavior during reasoning. Two concrete methods: (1). In-context learning and (2). Supervised fine-tuning are experimented using 7B models to 600B Deepseek-V3. Our results demonstrate consistent improvements across various tasks, with notable gains of up to 7.7\% on GSM8k and 12.5\% on DROP. Furthermore, the fine-tuned LLMs can incorporate sentence awareness evidenced by their internal representations. Our work establishes a simple yet effective technique for enhancing LLM's capabilities, offering promising directions for cognitive-inspired LLM enhancement paradigm.

cs.CL↗

arXiv2026

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness

Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based on response accuracy, causing models to suffer from severe label noise near the decision boundaries and consequently exhibit high rates of abstentions or hallucinations. This paper adopts a latent space representation perspective, revealing a "gray zone" near the decision hyperplane where internal belief ambiguity constitutes the core performance bottleneck. Based on this insight, we propose the **GeoDe** (**Geo**metric **De**noising) framework for abstention fine-tuning. This method constructs a truth hyperplane using linear probes and performs "geometric denoising" by employing geometric distance as a confidence signal for abstention decisions. This approach filters out ambiguous boundary samples while retaining high-fidelity signals for fine-tuning. Experiments across multiple models (Llama3, Qwen3) and benchmark datasets (TriviaQA, NQ, SciQ, SimpleQA) demonstrate that GeoDe significantly enhances model truthfulness and demonstrates strong generalization in out-of-distribution (OOD) scenarios. Code is available at https://github.com/Notbesidemoon/GeoDe.

cs.CL↗

arXiv2026

Investigating the intrinsic anomalous Hall effect in MnPt3 topological semimetal

The cubic Cu$_3$Au-type $X$Pt$_3$ family ($X$ = V, Cr, and Mn) is a topological semimetal characterized by anti-crossing gapped nodal lines near the Fermi level, which give rise to significant Berry curvatures and thus to the anomalous Hall effect (AHE). Among the three members, CrPt$_3$ has been experimentally verified to exhibit a large anomalous Hall conductivity (AHC), while its counterparts MnPt$_3$ and VPt$_3$ remain largely unexplored. Here, a series of MnPt$_3$ thin films with varying thicknesses (20--70 nm) was epitaxially grown on the MgO substrates using magnetron sputtering and was systematically investigated by magnetization, electrical resistivity, and Hall resistivity measurements. MnPt$_3$ films undergo a ferromagnetic transition at a Curie temperature $T_\mathrm{C}$, which increases as the film thickness increases, reaching $\sim$ 344 K for the 70-nm-thick film. All the anomalous Hall transport properties of MnPt$_3$ films, including the resistivity, conductivity, and angle, exhibit a strong correlation with their magnetic properties. The scaling analysis suggests that the intrinsic Berry-curvature mechanism dominates the observed AHE, while the extrinsic contributions are much smaller. The intrinsic AHC increases as the film thickness increases, while the extrinsic AHC is thickness-independent. Such an enhanced intrinsic AHC in the MnPt$_3$ films is most likely attributed to the strain effect, implying that it serves as an effective method to tune the electronic band topology in the $X$Pt$_3$ topological semimetal.

cond-mat.str-el↗

arXiv2026

Fast and Accurate Probing of In-Training LLMs' Downstream Performances

The paradigm of scaling Large Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive, therefore making the latency of LLM's in-training downstream performance evaluation unbearable. However, simple metrics like training loss (perplexity) are not always correlated with downstream performance, as sometimes their trends diverge from the actual task outcomes. This dilemma calls for a method that is computationally efficient and sufficiently accurate in measuring model capabilities. To address this challenge, we introduce a new in-training evaluation paradigm that uses a lightweight probe for monitoring downstream performance. The probes take the internal representations of LLM checkpoints (during training) as input and directly predict the checkpoint's performance on downstream tasks measured by success probability (i.e., pass@1). We design several probe architectures, validating their effectiveness using the OLMo3-7B's checkpoints across a diverse set of downstream tasks. The probes can accurately predict a checkpoint's performance (with avg. AUROC$>$0.75), have decent generalizability across checkpoints (earlier predicts later), and reduce the computation latency from $\sim$1 hr (using conventional generative evaluation method) to $\sim$3 min. In sum, this work presents a practical and scalable in-training downstream evaluation paradigm, enabling a more agile, informed, and efficient LLM development process.

cs.LG↗

arXiv2026

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware.

cs.LG↗

arXiv2026

SpecZoo: An AI-Powered Platform for Spectral Analysis and Visualization in Science and Education

Astronomical spectra, which encode rich astrophysical and chemical information, are fundamental to understanding celestial objects and universal laws. The advent of large-scale spectroscopic surveys, generating tens of millions of spectra, presents significant challenges for efficient data processing and analysis. To address these challenges, we develop an AI-powered platform (named ``SpecZoo'') for spectral visualization and analysis. This platform integrates modern information technology and machine learning to lower the barrier to spectral data utilization and enhance research efficiency. Its core functionalities include interactive visualization, automated spectral classification, physical parameter measurement, spectral annotation, and multi-band/multi-modal data fusion, all supported by flexible user and data management systems. It has become an essential tool for the National Astronomical Data Center, directly supporting spectral data processing and research for major projects including LAMOST, SDSS, DESI, and so on. Furthermore, the platform demonstrates strong potential for science-education integration, providing a novel resource for cultivating talent in astronomy and data science.

astro-ph.IM↗

arXiv2026

Engineering walk-off-induced orbital angular momentum spectrum in spontaneous parametric downconversion

Spontaneous parametric downconversion (SPDC) has been considered as a reliable source of high- dimensional entangled states in orbital angular momentum (OAM) basis. In real-world experiments, the spatial walk-off of the pump often degrades the fidelity of the generated quantum state. Since the walk-off effect breaks the rotational symmetry of the system, the conservation of total OAM is violated. Although the compensation of walk-off effects has become a well-established experimental technique, a systematic modal analysis of the spatial walk-off effect is still incomplete for SPDC. Here, we quantitatively analyze the violation of OAM conservation due to the pump walk-off effect in SPDC processes. We have derived a scaling law of the total OAM distribution with respect to the pump walk-off angle. We have also explored the feasibility of using the spatial walk-off as a mechanism to engineer the generated quantum state. Our study has provided guidelines for the generation of OAM-entangled state under realistic experimental conditions.

quant-ph↗

arXiv2026

Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning

Neuro-symbolic reasoning increasingly demands frameworks that unite the formal rigor of logic with the interpretability of large language models (LLMs). We introduce an end to end explainability by construction pipeline integrating the Automated Theorem Generator Delta1 based on the full triangular standard contradiction (FTSC) with LLMs. Delta1 deterministically constructs minimal unsatisfiable clause sets and complete theorems in polynomial time, ensuring both soundness and minimality by construction. The LLM layer verbalizes each theorem and proof trace into coherent natural language explanations and actionable insights. Empirical studies across health care, compliance, and regulatory domains show that Delta1 and LLM enables interpretable, auditable, and domain aligned reasoning. This work advances the convergence of logic, language, and learning, positioning constructive theorem generation as a principled foundation for neuro-symbolic explainable AI.

cs.LO↗

arXiv2026

Quantifying and extending the coverage of spatial categorization data sets

Variation in spatial categorization across languages is often studied by eliciting human labels for the relations depicted in a set of scenes known as the Topological Relations Picture Series (TRPS). We demonstrate that labels generated by large language models (LLMs) align relatively well with human labels, and show how LLM-generated labels can help to decide which scenes and languages to add to existing spatial data sets. To illustrate our approach we extend the TRPS by adding 42 new scenes, and show that this extension achieves better coverage of the space of possible scenes than two previous extensions of the TRPS. Our results provide a foundation for scaling towards spatial data sets with dozens of languages and hundreds of scenes.

cs.CL↗

arXiv2026

Field-theoretical approach to estimate mean gap and gap distribution in randomly rough surface contact mechanics

We extend the statistical field-theoretical framework of rough surface contact mechanics to characterize the interfacial gap between an elastic half-space and a randomly rough surface incorporating exponential repulsion. Building upon a cumulant expansion to second-order, we derive an explicit analytical relation between the mean gap and the applied normal pressure. This result provides a closed-form expression for the drift and diffusion coefficients in a convection-diffusion equation governing the scale-dependent evolution of the gap distribution. Solving this equation with appropriate initial and boundary conditions yields the gap distribution under varying external pressures. Both the mean gap and the gap distribution are found to be in good agreement with Green's function molecular dynamics (GFMD) simulations. Our results demonstrate that the field-theoretical approach enables quantitative predictions not only for contact stresses but also for interfacial gap in rough surface contacts.

cond-mat.soft↗

arXiv2026

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted $K$ nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with $N\!\in\![11,16]$ pedestrians in a $3\mathrm{m}\times3\mathrm{m}$ arena and evaluated up to $N\!=\!21$ pedestrians ($1.3\times$ denser), our policy reaches the goal in $>99\%$ of episodes and achieves $86\%$ collision-free success in random crowds, with markedly less freezing than analytical methods and a $>\!60$-point collision-free margin over learning-based benchmark methods. Codes are available at \href{https://github.com/jznmsl/PSS-Social}{https://github.com/jznmsl/PSS-Social}.

cs.LG↗

arXiv2026

Memory-Efficient 2D/3D Shape Assembly of Robot Swarms

Mean-shift-based approaches have recently emerged as a representative class of methods for robot swarm shape assembly. They rely on image-based target-shape representations to compute local density gradients and perform mean-shift exploration, which constitute their core mechanism. However, such representations incur substantial memory overhead, especially for high-resolution or 3D shapes. To address this limitation, we propose a memory-efficient tree representation that hierarchically encodes user-specified shapes in both 2D and 3D. Based on this representation, we design a behavior-based distributed controller for assignment-free shape assembly. Comparative 2D and 3D simulations against a state-of-the-art mean-shift algorithm show one to two orders of magnitude lower memory usage and two to four times faster shape entry. Physical experiments with 6 to 7 UAVs further validate real-world practicality.

cs.RO↗