arXiv subjects

Xintong Li

Publications and source records attributed to Xintong Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Expansion of Momentum Space and Full 2$π$ Solid Angle Photoelectron Collection in Laser-Based Angle-Resolved Photoemission Spectroscopy by Applying Sample Bias

Angle-resolved photoemission spectroscopy (ARPES) directly probes the energy and momentum of electrons in quantum materials, but conventional setups capture only a small fraction of the full 2$π$ solid angle. This limitation is acute in laser-based ARPES, where the low photon energy restricts momentum space despite ultrahigh resolution. Here we present systematic studies of bias ARPES, where applying a sample bias expands the accessible momentum range and enables full 2$π$ solid angle collection in two dimension using our 6.994 eV laser source. An analytical conversion relation is established and validated to accurately map the detector angle to the emission angle and the electron momentum in two dimensions. A precise approach is developed to determine the sample work function which is critical in the angle-momentum conversion of the bias ARPES experiments. Energy and angular resolutions are preserved under biases up to 100 V, and minimizing beam size is shown to be crucial. The technique is effective both near normal and off-normal geometries, allowing flexible Brillouin zone access with lower biases. Bias ARPES thus elevates laser ARPES to a new level, extending momentum coverage while retaining high resolution, and is applicable across a broad photon-energy range.

cond-mat.supr-con↗

arXiv2026

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length penalties, which cannot distinguish essential from redundant reasoning steps and therefore yield blunt compression. Although recent work incorporates step-level signals, such as offline pruning, supervised data construction, or verifier-based intermediate rewards, reasoning length is rarely treated as an explicit step-level optimization objective during RL. We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution. We estimate step importance from the model's on-policy log-probability improvement toward the correct answer, then treat excess length as a penalty mass redistributed to penalize low-importance steps more heavily while preserving high-importance reasoning. We optimize with a unified outcome-process advantage within group-relative policy optimization. Extensive experiments demonstrate that SWAP reduces reasoning length by 64.3% on average while improving accuracy by 5.7% relative to the base model.

cs.CL↗

arXiv2026

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to realize relative gains, leading to inefficient reasoning and overthinking, and complicating the trade-off between correctness and rollout efficiency. Controlling this behavior is difficult in practice, considering (i) Length penalties are hard to calibrate because longer rollouts may reflect harder problems that require longer reasoning, penalizing tokens risks truncating useful reasoning along with redundant continuation; and (ii) supervision that directly indicates when to continue or stop is typically unavailable beyond final answer correctness. We propose Weakly Supervised GRPO (WS-GRPO), which improves rollout efficiency by converting terminal rewards into correctness-aware guidance over partial trajectories. Unlike global length penalties that are hard to calibrate, WS-GRPO trains a preference model from outcome-only correctness to produce prefix-level signals that indicate when additional continuation is beneficial. Thus, WS-GRPO supplies outcome-derived continue/stop guidance, reducing redundant deliberation while maintaining accuracy. We provide theoretical results and empirically show on reasoning benchmarks that WS-GRPO substantially reduces rollout length while remaining competitive with GRPO baselines.

cs.LG↗

arXiv2026

AMPS: Adaptive Modality Preference Steering via Functional Entropy

Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may over-rely on linguistic priors relative to visual evidence, or conversely over-attend to visually salient but facts in textual contexts. Prior work has applied a uniform steering intensity to adjust the modality preference of MLLMs. However, strong steering can impair standard inference and increase error rates, whereas weak steering is often ineffective. In addition, because steering sensitivity varies substantially across multimodal instances, a single global strength is difficult to calibrate. To address this limitation with minimal disruption to inference, we introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering. Building on these insights, we propose a scaling strategy that reduces steering for sensitive samples and a learnable module that infers scaling patterns, enabling instance-aware control of modality preference. Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference, achieving effective adjustment while keeping generation error rates low.

cs.LG↗

arXiv2026

Electronic Structure and Superconducting Gap of HgBa$_2$Ca$_2$Cu$_3$O$_{8+δ}$ Revealed by Laser-Based Angle-Resolved Photoemission Spectroscopy

The spatially-resolved laser-based high resolution angle resolved photoemission spectroscopy (ARPES) measurements have been performed on the optimally-doped HgBa$_2$Ca$_2$Cu$_3$O$_{8+δ}$ (Hg1223) superconductor with a $T_c$ at 133 K. Two distinct regions are identified on the cleaved surface: the single Fermi surface region where only one Fermi surface is observed, and the double Fermi surface region where two Fermi surface sheets are resolved coming from both the inner (IP) and outer (OP) CuO$_2$ planes. The electronic structure and superconducting gap are measured on both of these two regions. In both cases, the observed electronic states are mainly concentrated near the nodal region. The momentum dependence of superconducting gap deviates from the standard d-wave form. These results indicate that the surface electronic structure of Hg1223 behaves more like that of underdoped cuprates.

cond-mat.supr-con↗

arXiv2026

Electronic Origin of Density Wave Orders in a Trilayer Nickelate

The discovery of superconductivity in Ruddlesden-Popper nickelates has established a new frontier in the study of high-temperature superconductors. However, the underlying pairing mechanism and its relationship to the material's electronic and magnetic ground states remain elusive. Since unconventional superconductivity often emerges from a complex interplay of magnetic correlations, elucidating the magnetic ground state of the nickelates at ambient pressure is crucial for understanding the emergence of superconductivity under high pressure. Here, we combine high-resolution angle-resolved photoemission spectroscopy with tight-binding model simulation to investigate the electronic structure of the representative trilayer Ruddlesden-Popper nickelate La$_4$Ni$_3$O$_{10}$. We provide the first experimental evidence of band splitting induced by interlayer coupling and further resolve the momentum-dependent density wave gap structures along all the Fermi surfaces. Our findings identify the mirror-selective Fermi surface nesting as the origin of the interlayer antiferromagnetic spin density wave and demonstrate the dominant role of Ni-3d$_{z^2}$ orbitals in the low-energy physics of La$_4$Ni$_3$O$_{10}$. These results provide a fundamental framework for understanding the magnetic interactions and high-temperature superconductivity mechanism in the Ruddlesden-Popper nickelate family.

cond-mat.supr-con↗

arXiv2026

CTRLS: Chain-of-Thought Reasoning via Latent State-Transition

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparency and performance in reasoning tasks. However, conventional CoT methods rely on heuristic sampling without structured modeling of reasoning transitions, constraining their ability to systematically explore and discover diverse and effective reasoning trajectories. In this work, we introduce CTRLS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions, enabling principled and state-aware exploration via distributional reinforcement learning. By modelling reasoning actions as explicit probability distributions in latent space, our approach explicitly models epistemic uncertainty, facilitating robust exploration of the reasoning space. As part of our framework, we introduce an on-policy reinforcement learning strategy incorporating epsilon-greedy exploration and entropy-based regularization to iteratively refine latent state transitions without requiring additional fine-tuning of the underlying LLM. Theoretical analyses provide evidence lower bounds (ELBO), theoretically grounding our transition-aware modeling of latent reasoning dynamics. Further experiments demonstrate improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.

cs.LG↗

arXiv2026

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.

cs.CL↗

arXiv2026

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent

Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue, often compressing visual representations and prioritizing task alignment over visual retention, which further worsens visual forgetting. To overcome this limitation, we introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation richness, interpreting this degradation through the information bottleneck principle as excessive compression that leads to the degradation of crucial pre-trained visual knowledge. Building on this view, we propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations while mitigating the over-compression effects described by the information bottleneck. By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation. To enable lightweight instruction-tuning, we further develop a memory-efficient fine-tuning approach using gradient masking, which selectively updates a subset of model parameters to enable parameter-efficient fine-tuning (PEFT), reducing computational overhead while preserving rich visual representations. Extensive experiments across various downstream tasks and backbone MLLMs demonstrate that MDGD effectively mitigates visual forgetting from pre-trained tasks while enabling strong adaptation to new tasks.

cs.LG↗

arXiv2026

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning

Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existing memory systems often store isolated records and retrieve fragments, limiting their ability to consolidate evolving user states and resolve conflicts. We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory. Episodic Trace Formation converts dialogue streams into MemCells that capture episodic traces, atomic facts, and time-bounded Foresight signals. Semantic Consolidation organizes MemCells into thematic MemScenes, distilling stable semantic structures and updating user profiles. Reconstructive Recollection performs MemScene-guided agentic retrieval to compose the necessary and sufficient context for downstream reasoning. Experiments on LoCoMo and LongMemEval show that EverMemOS achieves state-of-the-art performance on memory-augmented reasoning tasks. We further report a profile study on PersonaMem v2 and qualitative case studies illustrating chat-oriented capabilities such as user profiling and Foresight. Code is available at https://github.com/EverMind-AI/EverMemOS.

cs.AI↗

arXiv2026

SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as hallucinated entities, mis-grounded relations, skipped steps, and over-specified reasoning. Existing preference-based approaches, typically relying on textual perturbations or answer-conditioned rationales, fail to address this challenge as they allow models to exploit language priors to bypass visual grounding. To address this, we propose SceneAlign, a framework that leverages scene graphs as structured visual information to perform controllable structural interventions. By identifying reasoning-critical nodes and perturbing them through four targeted strategies that mimic typical grounding failures, SceneAlign constructs hard negative rationales that remain linguistically plausible but are grounded in inaccurate visual facts. These contrastive pairs are used in Direct Preference Optimization to steer models toward fine-grained, structure-faithful reasoning. Across seven visual reasoning benchmarks, SceneAlign consistently improves answer accuracy and reasoning faithfulness, highlighting the effectiveness of grounding-aware alignment for multimodal reasoning.

cs.CV↗

arXiv2025

Spatio-Temporal Hierarchical Causal Models

The abundance of fine-grained spatio-temporal data, such as traffic sensor networks, offers vast opportunities for scientific discovery. However, inferring causal relationships from such observational data remains challenging, particularly due to unobserved confounders that are specific to units (e.g., geographical locations) yet influence outcomes over time. Most existing methods for spatio-temporal causal inference assume that all confounders are observed, an assumption that is often violated in practice. In this paper, we introduce Spatio-Temporal Hierarchical Causal Models (ST-HCMs), a novel graphical framework that extends hierarchical causal modeling to the spatio-temporal domain. At the core of our approach is the Spatio-Temporal Collapse Theorem, which shows that a complex ST-HCM converges to a simpler flat causal model as the amount of subunit data increases. This theoretical result enables a general procedure for causal identification, allowing ST-HCMs to recover causal effects even in the presence of unobserved, time-invariant unit-level confounders, a scenario where standard non-hierarchical models fail. We validate the effectiveness of our framework on both synthetic and real-world datasets, demonstrating its potential for robust causal inference in complex dynamic systems.

stat.ML↗

arXiv2025

Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise comparisons, generating a single negative image via basic perturbations or similarity-based retrieval, which fail to capture the complex nature of multimodal preferences, inducing optimization bias and hallucinations. To address this issue, we propose MISP-DPO, the first framework to incorporate multiple, semantically diverse negative images in multimodal DPO via the Plackett-Luce model. Our method embeds prompts and candidate images in CLIP (Contrastive Language-Image Pretraining) space and applies a sparse autoencoder to uncover semantic deviations into interpretable factors. Negative samples are selected based on reconstruction difficulty, semantic deviation from the positive, and mutual diversity, yielding broader and more informative supervision. To handle multi-negative comparisons, we adopt a Plackett-Luce objective and introduce an importance sampling strategy that improves training efficiency. Experiments across five diverse benchmarks demonstrate that MISP-DPO consistently improves multimodal alignment over prior methods, validating the effectiveness of semantic-aware, multi-negative sampling in preference-based learning.

cs.CV↗

arXiv2025

GUI Agents: A Survey

Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods. We propose a unified framework that delineates their perception, reasoning, planning, and acting capabilities. Furthermore, we identify important open challenges and discuss key future directions. Finally, this work serves as a basis for practitioners and researchers to gain an intuitive understanding of current progress, techniques, benchmarks, and critical open problems that remain to be addressed.

cs.AI↗

arXiv2025

CoMMIT: Coordinated Multimodal Instruction Tuning

Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy between the two modules so that LLMs can adapt their reasoning abilities to downstream tasks while feature encoders can adjust to provide more task-specific information about its modality. In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives, where we find the unbalanced learning between the feature encoder and the LLM can cause problems of oscillation and biased learning that lead to sub-optimal convergence. Inspired by our findings, we propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning. Based on this, we further design a dynamic learning scheduler that better coordinates the learning between the LLM and feature encoder, alleviating the problems of oscillation and biased learning. In addition, we introduce an auxiliary regularization on the gradient to promote updating with larger step sizes, which potentially allows for a more accurate estimation of the proposed MultiModal Balance Coefficient and further improves the training sufficiency. Our proposed approach is agnostic to the architecture of LLM and feature encoder, so it can be generically integrated with various MLLMs. We conduct experiments on multiple downstream tasks with various MLLMs, demonstrating that the proposed method is more effective than the baselines in MLLM instruction tuning.

cs.LG↗

arXiv2025

Doping Evolution of Nodal Electron Dynamics in Trilayer Cuprate Superconductor Bi$_2$Sr$_2$Ca$_2$Cu$_3$O$_{10+δ}$ Revealed by Laser-Based Angle-Resolved Photoemission Spectroscopy

The doping evolution of the nodal electron dynamics in the trilayer cuprate superconductor Bi$_2$Sr$_2$Ca$_2$Cu$_3$O$_{10+δ}$ (Bi2223) is investigated using high-resolution laser-based angle-resolved photoemission spectroscopy (ARPES). Bi2223 single crystals with different doping levels are prepared by controlled annealing which cover the underdoped, optimally-doped and overdoped regions. The electronic phase diagram of Bi2223 is established which describes the T$_\mathrm{c}$ dependence on the sample doping level. The doping dependence of the nodal Fermi momentum for the outer (OP) and inner (IP) CuO$_2$ planes is determined. Charge distribution imbalance between the OP and IP CuO$_2$ planes is quantified, showing enhanced disparity with increasing doping. Nodal band dispersions demonstrate a prominent kink at $\sim$94$\,$meV in the IP band, attributed to the unique Cu coordination in the IP plane, while a weaker $\sim$60$\,$meV kink is observed in the OP band. The nodal Fermi velocity of both OP and IP bands is nearly constant at $\sim$1.62$\,$eVÅ independent of doping. These results provide important information to understand the origin of high T$_\mathrm{c}$ and superconductivity mechanism in high temperature cuprate superconductors.

cond-mat.supr-con↗

arXiv2025

Uniform well-posedness and Inviscid limit for the KdV-Burgers and mKdV-Burgers equations on $\mathbb{T}$

This article investigates uniform well-posedness and inviscid limit behavior for the periodic Korteweg-de Vries-Burgers (KdV-B) and modified Korteweg-de Vries-Burgers (mKdV-B) equations: \[ \partial_t u + \partial_x^3 u - \varepsilon \partial_x^2 u = \partial_x(u^α), \quad u(0) = ϕ, \] where $α= 2, 3$, $\varepsilon \in (0, 1]$ is the diffusion coefficient, and $u : \mathbb{R}^+ \times \mathbb{T} \to \mathbb{R}$ is real-valued. For the KdV-B equation ($α=2$), we establish unconditional uniform global well-posedness in $H^s(\mathbb{T})$ for $s \geq 0$, uniformly for all $\varepsilon \in [0,1]$, without relying on auxiliary function spaces. Furthermore, we prove that for any $s \geq 0$, there exists $T > 0$ such that solutions converge in $C([0,T]; H^s)$ to those of the KdV equation as $\varepsilon \to 0$. For the mKdV-B equation ($α=3$), we establish analogous results--unconditional uniform well-posedness and inviscid limit behavior in $H^s(\mathbb{T})$ for $s \geq 1/2$.

math.AP↗

arXiv2025

Field-induced spin continuum in twin-free Na$_3$Co$_2$SbO$_6$ revealed by magneto-THz spectroscopy

The honeycomb magnet Na$_3$Co$_2$SbO$_6$ recently emerged as a promising candidate for realizing Kitaev quantum spin liquid with relatively low levels of structural disorder. While the precise spin Hamiltonian remains controversial, the potential existence of a quantum spin liquid or other novel quantum magnetic phases continues to stimulate investigation. Here, we study the temperature and magnetic field-dependent spin excitations of Na$_3$Co$_2$SbO$_6$ on a twin-free single crystal using magneto-terahertz (THz) spectroscopy, focusing on magnetic anisotropy and field-induced unusual phases. We observe a low-energy continuum excitation above $T_N$ and a 0.5 THz (2 meV) spin wave excitation in magnetic order under zero field. Upon applying an in-plane magnetic field, the spin waves transform to a magnetic continuum over an intermediate field range, above which the system enters a spin-polarized state. Crucially, the spin excitation spectra reveal striking anisotropy between the $\textbf{a}$ and $\textbf{b}$ crystallographic axes, demanding description by a strongly anisotropic spin model. These findings establish Na$_3$Co$_2$SbO$_6$ as a model system for investigating field-tunable quantum magnetism and potential spin liquid behavior in highly anisotropic systems.

cond-mat.str-el↗