Searcharxiv⌕ Search

arXiv subjects

Wei Xia

Publications and source records attributed to Wei Xia.

At least 55 records · Page 3Linked to original sources
arXiv2026

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations-such as translating, rotating, or resizing objects-due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations. Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.

cs.CV↗
arXiv2026

Characterization of strongly convex Kähler-Berwald metrics

Let $F: T^{1,0}M\rightarrow[0,+\infty)$ be a strongly convex complex Finsler metric on a complex manifold $M$ and $\pmb{J}$ the canonical complex structure on the complex manifold $T^{1,0}M$. We give a geometric characterization of strongly convex Kähler-Berwald metrics. In particular, we prove that $\pmb{J}$ is horizontally parallel with respect to the Cartan connection iff $F$ is a Kähler-Berwald metric. We also prove that the Cartan connection and the Chern-Finsler connection associated to $F$ coincide iff $\pmb{J}$ is both horizontal and vertical parallel with respect to the Cartan connection. Based on these results, we give a rigidity theorem of strongly convex Kähler-Berwald metrics with constant holomorphic sectional curvatures.

math.DG↗
arXiv2026

AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing

Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences. Existing KT models typically follow a single-step training paradigm, which leads to discrepancies with the multi-step inference process required in real-world simulations, resulting in significant error accumulation. This accumulation of error, coupled with the issue of data sparsity, can substantially degrade the performance of recommendation models in the intelligent tutoring systems. To address these challenges, we propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT), which, for the first time, focuses on the multi-step KT task. More specifically, AdvKT leverages adversarial learning paradigm involving a generator and a discriminator. The generator mimics high-reward responses, effectively reducing error accumulation across multiple steps, while the discriminator provides feedback to generate synthetic data. Additionally, we design specialized data augmentation techniques to enrich the training data with realistic variations, ensuring that the model generalizes well even in scenarios with sparse data. Experiments conducted on four real-world datasets demonstrate the superiority of AdvKT over existing KT models, showcasing its ability to address both error accumulation and data sparsity issues effectively.

cs.LG↗
arXiv2025

Isotropic Dirac fermion and anomalous oscillator strength of zeroth Landau level transition

Dirac fermions, characterized by their linear dispersion and relativistic nature, have emerged as a prominent class of quasiparticles in condensed matter physics. While the Dirac equation, initially developed in the context of high-energy physics, provides a remarkable framework for describing the electronic properties of these materials, the inherent symmetry constraints of condensed matter often lead to deviations from the idealized paradigm. In particular, three-dimensional Dirac fermions in solids often exhibit anisotropic behavior, challenging the notion of perfect symmetry inherent in the Dirac equation. Here, we report the observation of isotropic massive Dirac fermions in LaAlSi through Landau level spectroscopy. The presence of three-dimensional massive Dirac fermions across the Fermi energy is demonstrated by quantized and semiclassical analyses of the magnetic field evolution of Landau level transitions. The isotropic topological nature, Fermi velocity, and Dirac mass are evidenced by the identical magneto-infrared response among the Faraday and three Voigt geometries. Furthermore, we observe an unusually large oscillator strength in the zeroth Landau level transition of the Dirac fermion, compared to transitions with higher indices. This phenomenon, supported by model calculations, can be attributed to the combined effects of the partial excitation of Dirac fermion and the resonant dielectric coupling with the Weyl plasma. Our work provides a strategy for realizing ideal quasiparticle excitations and their coupling effects in condensed matter systems, offering a platform for exploring relativistic physics.

cond-mat.mtrl-sci↗
arXiv2025

Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis

LLMs internally organize political ideology along low-dimensional structures that are partially, but not fully aligned with human ideological space. This misalignment is systematic, model specific, and measurable. We introduce a lightweight linear probe that both quantifies the misalignment and minimally corrects the output layer. This paper introduces a simple and efficient method for aligning models with specific user opinions. Instead of retraining the model, we calculated a bias score from its internal features and directly adjusted the final output probabilities. This solution is practical and low-cost and preserves the original reasoning power of the model.

cs.CL↗
arXiv2025

Obstructions of deforming complex structures and cohomology contractions

The Kodaira principle asserts that suitable cohomological contraction maps annihilate obstructions to deforming complex structures. In this paper, we revisit these phenomena from a purely analytic point of view, developing a refined power series method for the deformation of $(p,q)$-forms and complex structures. Working with the Frölicher spectral sequence, we show that under natural partial vanishing conditions on its differentials, all obstruction classes lie in the kernel of the corresponding contraction maps. This yields a refined Kodaira principle that recovers and strictly extends the known results. As a main application, we obtain new unobstructedness criteria for compact complex manifolds with trivial canonical bundle.

math.CV↗
arXiv2025

SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning

With the rapid advancement of large language models (LLMs), their deployment in real-world applications has become increasingly widespread. LLMs are expected to deliver robust performance across diverse tasks, user preferences, and practical scenarios. However, as demands grow, ensuring that LLMs produce responses aligned with human intent remains a foundational challenge. In particular, aligning model behavior effectively and efficiently during inference, without costly retraining or extensive supervision, is both a critical requirement and a non-trivial technical endeavor. To address the challenge, we propose SDA (Steering-Driven Distribution Alignment), a training-free and model-agnostic alignment framework designed for open-source LLMs. SDA dynamically redistributes model output probabilities based on user-defined alignment instructions, enhancing alignment between model behavior and human intents without fine-tuning. The method is lightweight, resource-efficient, and compatible with a wide range of open-source LLMs. It can function independently during inference or be integrated with training-based alignment strategies. Moreover, SDA supports personalized preference alignment, enabling flexible control over the model response behavior. Empirical results demonstrate that SDA consistently improves alignment performance across 8 open-source LLMs with varying scales and diverse origins, evaluated on three key alignment dimensions, helpfulness, harmlessness, and honesty (3H). Specifically, SDA achieves average gains of 64.4% in helpfulness, 30% in honesty and 11.5% in harmlessness across the tested models, indicating its effectiveness and generalization across diverse models and application scenarios.

cs.CL↗
arXiv2025

Experience-Guided Adaptation of Inference-Time Reasoning Strategies

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing designs only steer the system by modifying textual input to a language model or agent, which means that they cannot change sampling parameters, remove tools, modify system prompts, or switch between agentic and workflow paradigms. On the other hand, systems that adapt more flexibly require offline optimization and remain static once deployed. We present Experience-Guided Reasoner (EGuR), which generates tailored strategies -- complete computational procedures involving LLM calls, tools, sampling parameters, and control logic -- dynamically at inference time based on accumulated experience. We achieve this using an LLM-based meta-strategy -- a strategy that outputs strategies -- enabling adaptation of all strategy components (prompts, sampling parameters, tool configurations, and control logic). EGuR operates through two components: a Guide generates multiple candidate strategies conditioned on the current problem and structured memory of past experiences, while a Consolidator integrates execution feedback to improve future strategy generation. This produces complete, ready-to-run strategies optimized for each problem, which can be cached, retrieved, and executed as needed without wasting resources. Across five challenging benchmarks (AIME 2025, 3-SAT, and three Big Bench Extra Hard tasks), EGuR achieves up to 14% accuracy improvements over the strongest baselines while reducing computational costs by up to 111x, with both metrics improving as the system gains experience.

cs.AI↗
arXiv2025

Learning to Focus: Focal Attention for Selective and Scalable Transformers

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective feature selection at every layer of these models, particularly for long contexts. We propose Focal Attention, a simple yet effective modification that sharpens the attention distribution by controlling the softmax temperature, either as a fixed hyperparameter or as a learnable parameter during training. This sharpening enables the model to concentrate on the most relevant tokens while suppressing irrelevant ones. Empirically, Focal Attention scales more favorably than standard transformer with respect to model size, training data, and context length. Across diverse benchmarks, it achieves the same accuracy with up to 42% fewer parameters or 33% less training data. On long-context tasks, it delivers substantial relative improvements ranging from 17% to 82%, demonstrating its effectiveness in real world applications.

cs.CL↗
arXiv2025

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation

Tree search methods have demonstrated impressive performance in code generation. Previous methods combine tree search with reflection that summarizes past mistakes to achieve iterative improvement. However, these methods face significant challenges. First, they search directly within the code language space, neglecting the underlying reasoning process critical for effective code generation. Second, reflection-based approaches merely accumulate historical errors in memory without providing correct reasoning pathways, making it difficult for subsequent search iterations to identify optimal solutions, resulting in decreased search quality. In this work, we propose RethinkMCTS, a framework that systematically explores and refines the reasoning process for code generation. Specifically, we employ MCTS to search for thoughts before code generation and integrate MCTS with a refinement mechanism called rethink, which incorporates fine-grained code execution feedback to refine erroneous thoughts during the search. It ensures the search path aligns with better reasoning, improving overall search quality. Through extensive experiments, we demonstrate that RethinkMCTS outperforms previous search-based and feedback-enhanced code generation baselines.

cs.SE↗
arXiv2025

Diagnosing Quantum Many-body Chaos in Non-Hermitian Quantum Spin Chain via Krylov Complexity

We investigate the phase transitions from chaotic to nonchaotic dynamics in a quantum spin chain with a local non-Hermitian disorder, which can be realized with a Rydberg atom array setting. As the disorder strength increases, the emergence of nonchaotic dynamics is qualitatively captured through the suppressed growth of Krylov complexity, and quantitatively identified through the reciprocity breaking of Krylov space. We further find that the localization in Krylov space generates another transition in the weak disorder regime, suggesting a weak ergodicity breaking. Our results closely align with conventional methods, such as the entanglement entropy and complex level spacing statistics, and pave the way to explore non-Hermitian phase transitions using Krylov complexity and associated metrics.

quant-ph↗
arXiv2025

LATTS: Locally Adaptive Test-Time Scaling

One common strategy for improving the performance of Large Language Models (LLMs) on downstream tasks involves using a \emph{verifier model} to either select the best answer from a pool of candidates or to steer the auto-regressive generation process towards better outputs. This class of methods typically results in improved accuracy at the cost of increased computation at test-time, a paradigm known as \emph{test-time scaling}. However, most existing approaches increase computation uniformly across all samples and generation steps, without considering the complexity of individual instances, leading to inefficient resource use. We address this limitation by proposing an approach, called \emph{Locally Adaptive Test-Time Scaling (LATTS)}, that allocates variable compute across generation steps. Specifically, at each generation step, LATTS employs a verifier-based acceptance criterion to decide whether to resample, backtrack, restart, or stop the generation process. This criterion effectively adjusts the per-step computational effort based on a precise notion of \emph{local difficulty} derived from the verifier model. Empirical results show that LATTS achieves significantly superior accuracy--compute tradeoffs compared to standard verifier-based methods.

cs.AI↗
arXiv2025

Multi-origin driven giant planar Hall effect in topological antiferromagnet EuAl2Si2 with tunable spin texture

In topological materials, the planar Hall effect (PHE) is often regarded as a hallmark of profound quantum phenomena-most notably the Adler-Bell-Jackiw chiral anomaly and Berry curvature-rendering it an indispensable tool for deciphering the topological essence of emergent phases. In this study, we delve into the PHE and anisotropic magnetoresistance in the recently discovered layered topological antiferromagnet EuAl2Si2. Our analysis of the robust PHE signal (~3.8 μΩ cm at 2 K and 8 T) unveils a distinct interplay of mechanisms. While Berry curvature plays a minor role, the dominant contributions stem from classical orbital MR in the field-induced ferromagnetic state and field-suppressed spin fluctuations in the paramagnetic regime. These insights not only position EuAl2Si2-with its highly tunable spin texture-as an exemplary system for probing the intricate coupling between spin configurations and band topology in magnetotransport but also pave the way for designing novel materials with tailored PHE responses, highlighting significant application prospects in quantum sensing, spintronic devices, and topologically protected electronic systems.

cond-mat.str-el↗
arXiv2025

Sliding two-dimensional superconductivity and charge-density-wave state in a bulk crystal

Superconductivity in the two-dimensional (2D) limit is a fertile ground for exotic quantum phenomena-many of which remain elusive in their 3D counterparts. While studies of 2D superconductivity have predominantly focused on mono- or few-layer systems, we demonstrate an alternative route-interlayer sliding in bulk crystals. Through a precisely controlled growth strategy, we engineer interlayer sliding in bulk 3R-NbSe2, deliberately disrupting [001] mirror symmetry and drastically suppressing interlayer coupling. Remarkably, this structural manipulation stabilizes Ising-type superconductivity coexisting with an unconventional charge-density-wave (CDW) state akin to that of monolayer 2H-NbSe2. The sliding phase exhibits a pronounced suppression of the upper critical field at low temperatures, revealing a delicate competition between Ising and Rashba spin-orbit coupling (SOC) in the globally noncentrosymmetric lattice. Intriguingly, the superconducting state displays two-fold symmetry, a signature that may arise from asymmetric SOC or a multi-component pairing order parameter. Our work establishes interlayer sliding as a symmetry-breaking tool to promote 2D superconductivity in bulk materials-without resorting to extrinsic intercalation or doping. More broadly, this approach sets a paradigm for unlocking hidden quantum states in layered materials, offering a new dimension in design of quantum matter.

cond-mat.supr-con↗
arXiv2025

Quantum complexity phase transition in fermionic quantum circuits

Understanding the complexity of quantum many-body systems has been attracting much attention recently for its fundamental importance in characterizing complex quantum phases beyond the scope of quantum entanglement. Here, we investigate Krylov complexity in quantum percolation models (QPM) and establish unconventional phase transitions emergent from the interplay of exponential scaling of the Krylov complexity and the number of spanning clusters in QPM. We develop a general scaling theory for Krylov complexity phase transitions (KCPT) on QPM, and obtain exact results for the critical probabilities and exponents. For non-interacting systems across diverse lattices (1D/2D/3D regular, Bethe, and quasicrystals), our scaling theory reveals that the KCPT coincides with the classical percolation transition. In contrast, for interacting systems, we find the KCPT develops a generic separation from the percolation transition due to the highly complex quantum many-body effects, which is analogous to the Griffiths effect in the critical disorder phase transition. To test our theoretical predictions, we provide a concrete protocol for measuring the Krylov complexity, which is accessible to present experiments.

quant-ph↗
arXiv2025

Giant plateau-like topological Hall effect controlled by tailoring the magnetic exchange stiffness in a kagome magnet

The ferrimagnet TbMn6Sn6 has attracted vast attention, because its pristine Mn kagome lattice with strong spin-orbit coupling and out-of-plane Tb-Mn exchange supports quantum-limit Chern topological magnetism which can be described by the simple spinless Haldane model. We unveil herein that engineering the kagome lattice through partial substitution of Mn with nonmagnetic Cr induces a striking structural reorganization-Cr preferentially concentrates within a single Mn layer per unit cell, reducing the crystal symmetry from the D6h point group to the C2. This tailored structure configuration gives rise to a plateau-like topological Hall effect (THE), achieving a record-breaking resistivity of 19.1 ohm cm among bulk systems. Complementary magnetic force microscopy measurements unveil a magnetic domain transition near 1 T at 180 K, aligning with the field-dependent phase diagram of the THE. Our direct visualization of the magnetic domain structure underscores the critical role of broken kagome lattice symmetry in generating distinct exchange stiffness between the two Mn layers. These findings establish a new paradigm for exploring exotic states in kagome topological magnets and provide a proof-of-principle strategy for unraveling the interplay between magnetism and emergent topological properties in kagome systems.

cond-mat.str-el↗
arXiv2025

Deformed Aeppli cohomology: canonical deformations and jumping formulas

Given a complex analytic family of complex manifolds, we consider canonical Aeppli deformations of $(p,q)$-forms and study its relations to the varying of dimension of the deformed Aeppli cohomology $\dim H^{\bullet,\bullet}_{Aϕ(t)}(X)$. In particular, we prove the jumping formula for the deformed Aeppli cohomology $H^{\bullet,\bullet}_{Aϕ(t)}(X)$. As a direct consequence, $\dim H^{p,q}_{Aϕ(t)}(X)$ remains constant iff the Bott-Chern deformations of $(n-p,n-q)$-forms and the Aeppli deformations of $(n-p-1,n-q-1)$-forms are canonically unobstructed. Furthermore, the Bott-Chern/Aeppli deformations are shown to be unobstructed if some weak forms of $\partial\bar{\partial}$-lemma is satisfied.

math.DG↗