arXiv subjects

Run Yang

Publications and source records attributed to Run Yang.

At least 19 recordsLinked to original sources

arXiv2026

From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs

Scaling Transformers has driven large gains in language modeling, but transplanting this to behavior-sequence modeling in production ranking is challenging: recommendation differs in signal quality, where behavior sequences are noisy, temporally irregular, and sparsely supervised, and in computation asymmetry, where each request scores many candidates against one shared user history under tight latency budgets. We propose ReST, a recommendation-native Transformer scaling framework. For signal quality, it introduces a sequence encoder with dual-gated attention, rotary positional and temporal embedding, stabilized residual normalization, and training-only auxiliary objectives. For computation asymmetry, it factorizes ranking into a heavy reusable encoder and a lightweight cross decoder with projection-free KV attention and token-specific parameterization, coupling user-level shared-prefix training with shared-prefix serving for compute-once, decode-many-times ranking. Across industrial and public benchmarks, ReST achieves higher accuracy and scales more consistently along sequence length, depth, and width, where LLM-style Transformer blocks saturate. A one-week online A/B test on a production advertising platform improves online AUC by 1.31% and lifts a core revenue metric by 11.93% within a 50 ms P99 budget; ReST has since been fully deployed in production, showing that behavior-sequence scaling remains a promising, under-exploited axis for production ranking.

cs.IR↗

arXiv2026

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teacher probabilities only for sampled tokens. Yet it frequently suffers from diversity distillation failure: the student's pass@1 improves while its pass@$k$ plateaus, failing to inherit the teacher's diversity. To explain this, we introduce First-Order Local Entropy Influence, a signed first-order proxy that decouples each update's entropy effect into the teacher--student log-probability gap and the student's local probability structure, and empirically links entropy contraction to negative-influence positions. Motivated by this, we propose Influence-Directed Adaptive On-Policy Distillation (IDA-OPD): rather than relying on costly full-vocabulary Forward-KL objectives, it preserves entropy-expanding updates while replacing entropy-contracting ones with divergence-adaptive advantage shrinkage, using only the teacher's sampled-token log-probability. Experiments on reasoning-oriented distillation show IDA-OPD consistently improves pass@$k$, inheriting the teacher's diversity through distillation, matches the strongest teacher-informed methods at strictly lower cost, and broadly maintains vanilla OPD's pass@1, all without full-vocabulary teacher information.

cs.CL↗

arXiv2026

MemeMind: Reference-Guided Trace Construction for Offline Context Optimization

Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollouts on an adaptation set, but some queries produce only failed rollouts. In these cases, the optimizer sees no successful example of how the available tools can reach the correct answer. We introduce MemeMind, which uses an offline reference answer to recover this missing experience. TraceBuilder identifies the evidence required by the reference, executes text search, image retrieval, and visual grounding, and verifies the resulting tool trace before adding it to the adaptation buffer. ToolGuide then summarizes the collected traces into a shared guide and separate instructions for each tool. The reference answers and constructed traces are used only during adaptation, while inference uses the learned guides with a frozen model. We study this problem through Anime, Comic, and Game meme interpretation. These memes combine edited and ambiguous visual content, overlaid text, long tail franchise knowledge, and culture specific references. Their interpretation can require coordinated visual grounding, image retrieval, and text search, making them a demanding setting in which native rollout groups may fail together. We evaluate MemeMind on MemeX, a benchmark of 1,000 such memes annotated by experts. Across two Qwen3-VL models, two language partitions, and two independent judges, MemeMind improves over the strongest context optimization baseline by 22.0% and 21.1% on Qwen3-VL-30B-A3B, and by 8.1% and 8.0% on Qwen3-VL-235B-A22B under GPT-5 judging. Ablations and held out traces show that constructing successful tool use for failed groups provides the largest component gain and produces more effective evidence acquisition at inference time.

cs.CV↗

arXiv2026

Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile. In particular, we show that physically realizable adversarial patches can reliably induce failures by triggering a mechanism we call policy-critical action-to-vision attention hijacking, where action-conditioned attention is diverted from task-relevant regions to a localized patch. To demonstrate the threat, we propose Attention-Guided Semantic Disruption (AGSD), an Expectation-over-Transformation (EOT) optimized printable patch that jointly (i) concentrates action-to-vision attention on the patch and (ii) disrupts vision-language semantic alignment, yielding strong cross-task and cross-architecture transfer. To mitigate such attacks, we introduce Structure-Aware Robust Fine-Tuning (SARF), a zero-inference-overhead defense that fine-tunes only the visual encoder using feature anchoring, policy-critical attention correction, and language-guided geometric consistency restricted to semantically relevant regions. On LIBERO, SARF reduces OpenVLA's failure rate under AGSD from 100% to 14.2%-56.8% (28.6% average) across suites while preserving clean performance, and on a real PiPER manipulator it improves average success under AGSD from 23.0% to 65.0%. These results highlight mechanism-level robustness as a practical path to securing VLA robots against physical attention hijacking.

cs.RO↗

arXiv2026

MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes

Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels. Memes expose this gap because they rely on cultural entities, background knowledge, and community conventions. Most meme benchmarks reduce interpretation to labels or holistic scores, obscuring where an explanation breaks down. We introduce MemeBench, a diagnostic benchmark of 1,253 Chinese and English memes with human-written references and quality-controlled VIKR annotations, centered on anime, comics, games, and adjacent online subcultures. Its VIKR schema decomposes explanations into Visual clues, Identity links, Knowledge units, and Reasoning mechanisms. Across 26 LVLMs, every model covers visible content more reliably than the knowledge needed to interpret it, and even the strongest retains a 22.6% Visual-Knowledge gap. To test whether this diagnosis can guide improvement, we introduce KAR, an entity-guided retrieval baseline built on CultureBase. Across four controlled models, KAR raises VIKR Success by 3.6-7.4% and, compared with generic retrieval, repairs more answers and breaks fewer. Yet both retrieval conditions improve Identity and Knowledge while reducing Visual coverage in every comparison. MemeBench reveals whether an interpretation succeeds, what is missing, and whether targeted evidence fills the diagnosed gap.

cs.AI↗

arXiv2026

OPSDL: On-Policy Self-Distillation for Long-Context Language Models

Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-training methods have made progress in long-context scaling, they either rely on high-quality supervision data or sparse sequence-level rewards, leading to unstable and inefficient optimization. We propose OPSDL, an On-Policy Self-Distillation method for enhancing the Long-context capabilities of LLMs. Unlike other recent self-distillation methods that inject privileged information and rely on the model's in-context learning ability to act as a teacher, OPSDL leverages the model's own inherently strong short-context capability as a self-teacher to supervise its own generation in long-context scenarios. The model first generates responses conditioned on the full long-context, then the self-teacher provides per-token supervision signals via point-wise reverse KL divergence under the relevant extracted short-context. This dense token-level signal encourages faithful use of relevant evidence and mitigates hallucinations induced by irrelevant context. We evaluate OPSDL on long-context benchmarks across a range of models from 7B to 32B parameters. Results show consistent and substantial improvements across varying context lengths, outperforming standard post-training approaches such as SFT and DPO with higher sample efficiency. Notably, these gains are achieved without degrading general short-context performance. These findings highlight the effectiveness of OPSDL as a scalable and stable approach for long-context learning.

cs.CL↗

arXiv2025

StatEval: A Comprehensive Benchmark for Large Language Models in Statistics

Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do not reflect the layered, proof-driven nature of real statistical practice. To address this gap, we introduce \textbf{StatEval}, the first large-scale benchmark for statistical reasoning across curricular and research-level settings. StatEval includes over 100,000 curated problems, with 20,000+ foundational questions spanning undergraduate and graduate curricula and 80,000+ research-level proof tasks extracted from leading statistical journals. To construct StatEval, we develop \textbf{TRACE} (Topology and Reasoning-Aware Context Extractor), a multi-agent pipeline with human-in-the-loop validation that converts unstructured academic texts into self-contained theorem-level reasoning tasks. We also propose an Adaptive Process-Based Scoring Pipeline for complex statistical proofs, enabling fine-grained evaluation beyond final-answer matching. Experiments show that while LLMs perform reasonably on foundational tasks, they struggle with rigorous research-level reasoning. Beyond evaluation, StatEval serves as a resource for improving reasoning, as retrieval-augmented generation and domain-specific alignment consistently enhance performance. Together, these results establish StatEval as both a benchmark and an infrastructure for advancing statistical reasoning in LLMs.

cs.CL↗

arXiv2025

R1-RE: Cross-Domain Relation Extraction with RLVR

Relation extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels-an approach that often suffers from poor out-of-domain (OOD) generalization. Inspired by the workflow of human annotators, we reframe RE as a reasoning task guided by annotation guidelines and introduce R1-RE, the first reinforcement learning with verifiable reward (RLVR) framework for RE tasks. Our method elicits the reasoning abilities of small language models for annotation tasks, resulting in significantly improved OOD robustness. We evaluate our approach on the public Sem-2010 dataset and a private MDKG dataset. The R1-RE-7B model attains an average OOD accuracy of approximately 70%, on par with leading proprietary models such as GPT-4o. Additionally, our comprehensive analysis provides novel insights into the training dynamics and emergent reasoning behaviors of the RLVR paradigm for RE.

cs.CL↗

arXiv2025

Spatio-temporal Prediction of Fine-Grained Origin-Destination Matrices with Applications in Ridesharing

Accurate spatial-temporal prediction of network-based travelers' requests is crucial for the effective policy design of ridesharing platforms. Having knowledge of the total demand between various locations in the upcoming time slots enables platforms to proactively prepare adequate supplies, thereby increasing the likelihood of fulfilling travelers' requests and redistributing idle drivers to areas with high potential demand to optimize the global supply-demand equilibrium. This paper delves into the prediction of Origin-Destination (OD) demands at a fine-grained spatial level, especially when confronted with an expansive set of local regions. While this task holds immense practical value, it remains relatively unexplored within the research community. To fill this gap, we introduce a novel prediction model called OD-CED, which comprises an unsupervised space coarsening technique to alleviate data sparsity and an encoder-decoder architecture to capture both semantic and geographic dependencies. Through practical experimentation, OD-CED has demonstrated remarkable results. It achieved an impressive reduction of up to 45% reduction in root-mean-square error and 60% in weighted mean absolute percentage error over traditional statistical methods when dealing with OD matrices exhibiting a sparsity exceeding 90%.

cs.LG↗

arXiv2025

Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models

Large Language Models (LLMs) and Vision-Language Models (VLMs) have achieved impressive performance across a wide range of tasks, yet they remain vulnerable to carefully crafted perturbations. In this study, we seek to pinpoint the sources of this fragility by identifying parameters and input dimensions (pixels or token embeddings) that are susceptible to such perturbations. To this end, we propose a stability measure called \textbf{FI}, \textbf{F}irst order local \textbf{I}nfluence, which is rooted in information geometry and quantifies the sensitivity of individual parameter and input dimensions. Our extensive analysis across LLMs and VLMs (from 1.5B to 13B parameters) reveals that: (I) A small subset of parameters or input dimensions with high FI values disproportionately contribute to model brittleness. (II) Mitigating the influence of these vulnerable parameters during model merging leads to improved performance.

cs.LG↗

arXiv2024

Experimental progress in Eu(Al,Ga)$_4$ topological antiferromagnets

The non-trivial magnetic and electronic phases occurring in topological magnets are often entangled, thus leading to a variety of exotic physical properties. Recently, the BaAl$_4$-type compounds have been extensively investigated to elucidate the topological features appearing in their real- and momentum spaces. In particular, the topological Hall effect and the spin textures, typical of the centrosymmetric Eu(Al,Ga)$_4$ family, have stimulated extensive experimental and theoretical research. In this topical review, we discuss the latest findings regarding the Eu(Al,Ga)$_4$ topological antiferromagnets and related materials, arising from a vast array of experimental techniques. We show that Eu(Al,Ga)$_4$ represents a suitable platform to explore the interplay between lattice-, charge-, and spin degrees of freedom, and associated emergent phenomena. Finally, we address some key questions open to future investigation.

cond-mat.str-el↗

arXiv2024

Multitier Service Migration Framework Based on Mobility Prediction in Mobile Edge Computing

Mobile edge computing (MEC) pushes computing resources to the edge of the network and distributes them at the edge of the mobile network. Offloading computing tasks to the edge instead of the cloud can reduce computing latency and backhaul load simultaneously. However, new challenges incurred by user mobility and limited coverage of MEC server service arise. Services should be dynamically migrated between multiple MEC servers to maintain service performance due to user movement. Tackling this problem is nontrivial because it is arduous to predict user movement, and service migration will generate service interruptions and redundant network traffic. Service interruption time must be minimized, and redundant network traffic should be reduced to ensure service quality. In this paper, the container lives migration technology based on prediction is studied, and an online prediction method based on map data that does not rely on prior knowledge such as user trajectories is proposed to address this challenge in terms of mobility prediction accuracy.

cs.NI↗

arXiv2023

Critical-point anomalies in doped CeRhIn5

The heavy-fermion compound CeRhIn$_5$ can be tuned through a quantum critical point, when In is partially replaced by Sn. This way additional charge carriers are introduced and the antiferromagnetic order is gradually suppressed to zero temperature. Here we investigate the temperature-dependent optical properties of CeRh(In$_{1-x}$Sn$_x$)$_5$ single crystals for $x = 4.4\%$, $6.9\%$ and $9.8\%$. With increasing Sn concentration the infrared conductivity reveals a clear enhancement of the $c$-$f$ hybridization strength. At low temperatures we observed a non-Fermi-liquid behavior in the frequency dependence of the scattering rate and effective mass in all three compounds. In addition, below a characteristic temperature $T^* \approx 10$ K, the temperature dependent resistivity $\rho(T)$ follows a $\log T$ behavior, typical for a non-Fermi liquid. The temperature-dependent magnetization also exhibits anomalous behavior below $T^*$. Our investigation reveal that below $T^*$ the system shows a pronounced non-Fermi-liquid behavior and $T^*$ monotonically increases as the quantum critical point is approached.

cond-mat.str-el↗

arXiv2023

Directional diffusion models for graph representation learning

In recent years, diffusion models have achieved remarkable success in various domains of artificial intelligence, such as image synthesis, super-resolution, and 3D molecule generation. However, the application of diffusion models in graph learning has received relatively little attention. In this paper, we address this gap by investigating the use of diffusion models for unsupervised graph representation learning. We begin by identifying the anisotropic structures of graphs and a crucial limitation of the vanilla forward diffusion process in learning anisotropic structures. This process relies on continuously adding an isotropic Gaussian noise to the data, which may convert the anisotropic signals to noise too quickly. This rapid conversion hampers the training of denoising neural networks and impedes the acquisition of semantically meaningful representations in the reverse process. To address this challenge, we propose a new class of models called {\it directional diffusion models}. These models incorporate data-dependent, anisotropic, and directional noises in the forward diffusion process. To assess the efficacy of our proposed models, we conduct extensive experiments on 12 publicly available datasets, focusing on two distinct graph representation learning tasks. The experimental results demonstrate the superiority of our models over state-of-the-art baselines, indicating their effectiveness in capturing meaningful graph representations. Our studies not only provide valuable insights into the forward process of diffusion models but also highlight the wide-ranging potential of these models for various graph-related tasks.

cs.LG↗

arXiv2023

The discovery of three-dimensional Van Hove singularity

Arising from the extreme/saddle point in electronic bands, Van Hove singularity (VHS) manifests divergent density of states (DOS) and induces various new states of matter such as unconventional superconductivity. VHS is believed to exist in one and two dimensions, but rarely found in three dimension (3D). Here, we report the discovery of 3D VHS in a topological magnet EuCd2As2 by magneto-infrared spectroscopy. External magnetic fields effectively control the exchange interaction in EuCd2As2, and shift 3D Weyl bands continuously, leading to the modification of Fermi velocity and energy dispersion. Above the critical field, the 3D VHS forms and is evidenced by the abrupt emergence of inter-band transitions, which can be quantitatively described by the minimal model of Weyl semimetals. Three additional optical transitions are further predicted theoretically and verified in magneto-near-infrared spectra. Our results pave the way to exploring VHS in 3D systems and uncovering the coordination between electronic correlation and the topological phase.

cond-mat.mtrl-sci↗

arXiv2023

Pressure-induced coevolution of transport properties and lattice stability in CaK(Fe1-xNix)4As4 (x= 0.04 and 0) superconductors with and without spin-vortex crystal state

Here we report the first investigation on correlation between the transport properties and the corresponding stability of the lattice structure for CaK(Fe1-xNix)4As4 (x=0.04 and 0), a new type of putative topological superconductors, with and without a spin-vortex crystal (SVC) state in a wide pressure range involving superconducting to non-superconducting transition and the half- to full-collapse of tetragonal (h-cT and f-cT) phases, by the complementary measurements of high-pressure resistance, Hall coefficient and synchrotron X-ray diffraction. We identify the three critical pressures, P1 that is the turn-on critical pressure of the h-cT phase transition and it coincides with the critical pressure for the sign change of Hall coefficient from positive to negative, a manifestation of the Fermi surface reconstruction, P2 that is the turn-off pressures of the h-cT phase transition, and P3 that is the critical pressure of the f-cT phase transition. By comparing the high-pressure results measured from the two kinds of samples, we find a distinct left-shift of the P1 for the doped sample, at the pressure of which its SVC state is fully suppressed, however the P2 and the P3 remain the same as that of the undoped one. Our results not only provide a consistent understanding on the results reported before, but also demonstrate the importance of the Fe-As bonding in stabilizing the superconductivity of the iron pnictide superconductors through the pressure window.

cond-mat.supr-con↗

arXiv2022

The breakdown of both strange metal and superconducting states at a pressure-induced quantum critical point in iron-pnictide superconductors

The strange metal (SM) state, characterized by a linear-in-temperature resistivity, is often seen in the normal state of high temperature superconductors. It is believed that the SM state is one of the keys to understand the underlying mechanism of high-Tc superconductivity. Here we report the first observation of the concurrent breakdown of the SM normal state and superconductivity at a pressure-induced quantum critical point in an iron-pnictide superconductor, Ca10(Pt4As8)((Fe0.97Pt0.03)2As2)5. We find that, upon suppressing the superconducting state by applying pressure, the power exponent changes from 1 to 2, and the corresponding coefficient A, the slope of the temperature-linear resistivity per FeAs layer, gradually diminishes. At a critical pressure (12.5 GPa), A and Tc go to zero concurrently,where a quantum phase transition (QPT) from a superconducting state with a SM normal state to a non-superconducting Fermi liquid state takes place. Scaling analysis on the results obtained from the pressurized 1048 superconductor reveals that A and Tc have a positive relation, which exhibits a similarity with that is seen in other chemically-doped unconventional superconductors, regardless of the type of the tuning method (doping or pressurizing), the crystal structure, the bulk or film superconductors and the nature of dopant. These results suggest that there is a simple but powerful organizational principle of connecting the SM normal state with the high-Tc superconductivity.

cond-mat.supr-con↗

arXiv2021

Observation of optical gyromagnetic properties in a magneto-plasmonic metamaterial

Metamaterials with artificial optical properties have attracted significant research interest. In particular, artificial magnetic resonances in non-unity permeability tensor at optical frequencies in metamaterials have been reported. However, only non-unity diagonal elements of the permeability tensor have been demonstrated to date. A gyromagnetic permeability tensor with non-zero off-diagonal elements has not been observed at the optical frequencies. Here we report the observation of gyromagnetic properties in the near-infrared wavelength range in a magneto-plasmonic metamaterial. The non-zero off-diagonal permeability tensor element causes the transverse magneto-optical Kerr effect (TMOKE) under s-polarized incidence that otherwise vanishes if the permeability tensor is not gyromagnetic. By retrieving the permeability tensor elements from reflection, transmission, and TMOKE spectra, we show that the effective off-diagonal permeability tensor elements reach the 10-3 level at the resonance wavelength (~900 nm) of the split-ring resonators that is at least two orders of magnitude higher than that of magneto-optical materials at the same wavelength. The artificial gyromagnetic permeability is attributed to the change in the local electric field direction modulated by the split-ring resonators. Our study demonstrates the possibility of engineering the permeability and permittivity tensors in metamaterials at arbitrary frequencies, thereby promising a variety of applications of next-generation nonreciprocal photonic devices, magneto-plasmonic sensors, and active metamaterials.

physics.optics↗