Search arXiv⌕ Search

arXiv subjects

Yifan Li

Publications and source records attributed to Yifan Li.

At least 91 records · Page 5Linked to original sources
arXiv2026

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0.

cs.CV↗
arXiv2026

A Survey of Large Language Models

Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable AI algorithms for comprehending and grasping a language. As a major approach, language modeling has been widely studied for language understanding and generation in the past two decades, evolving from statistical language models to neural language models. Recently, pre-trained language models (PLMs) have been proposed by pre-training Transformer models over large-scale corpora, showing strong capabilities in solving various NLP tasks. Since researchers have found that model scaling can lead to performance improvement, they further study the scaling effect by increasing the model size to an even larger size. Interestingly, when the parameter scale exceeds a certain level, these enlarged language models not only achieve a significant performance improvement but also show some special abilities that are not present in small-scale language models. To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size. Recently, the research on LLMs has been largely advanced by both academia and industry, and a remarkable progress is the launch of ChatGPT, which has attracted widespread attention from society. The technical evolution of LLMs has been making an important impact on the entire AI community, which would revolutionize the way how we develop and use AI algorithms. In this survey, we review the recent advances of LLMs by introducing the background, key findings, and mainstream techniques. In particular, we focus on four major aspects of LLMs, namely pre-training, adaptation tuning, utilization, and capacity evaluation. Besides, we also summarize the available resources for developing LLMs and discuss the remaining issues for future directions.

cs.CL↗
arXiv2026

From Natural Language to Executable Option Strategies via Large Language Models

Large Language Models (LLMs) excel at general code generation, yet translating natural-language trading intents into correct option strategies remains challenging. Real-world option design requires reasoning over massive, multi-dimensional option chain data with strict constraints, which often overwhelms direct generation methods. We introduce the Option Query Language (OQL), a domain-specific intermediate representation that abstracts option markets into high-level primitives under grammatical rules, enabling LLMs to function as reliable semantic parsers rather than free-form programmers. OQL queries are then validated and executed deterministically by an engine to instantiate executable strategies. We also present a new dataset for this task and demonstrate that our neuro-symbolic pipeline significantly improves execution accuracy and logical consistency over direct baselines.

cs.AI↗
arXiv2026

Body-scale NFC for wearables: human-centric body-scale NFC networking for ultra-low-power wearable devices (Demo of UTokyo Kawahara Lab 2025)

Near Field Communication (NFC) is a promising technology for ultra-low-power wearables, yet its short communication range limits its use to narrow-area, point-to-point interactions. We propose a body-scale NFC networking system that extends NFC coverage around the body, enabling surface-to-multipoint communication with distributed NFC sensor tags. This demonstration introduces two key technologies: Meander NFC and picoRing NFC. First, Meander NFC expands a clothing-based NFC networking area up to body scale while enabling a stable readout of small NFC tags occupying 1% of the coverage area. Meander NFC uses a meander coil which creates a spatially confined inductive field along the textile surface, ensuring robust coupling with small tags while preventing undesired electromagnetic body coupling. Second, picoRing NFC solves the weak inductive coupling caused by distance and size mismatches. By leveraging middle-range NFC and coil optimization, picoRing NFC extends the communication range to connect these disparate nodes between the ring and wristband.

cs.NI↗
arXiv2026

Remember You: Understanding How Users Use Deadbots to Reconstruct Memories of the Deceased

Generative AI has enabled ``Deadbots'', offering mourners an interactive way to engage with simulations of the deceased. While existing research often emphasizes ethics, less is known about how bereaved individuals construct and reshape memory through such interactions. To address this gap, this study draws on in-depth interviews with 26 users. Findings reveal that users are not passive recipients but active constructors of the deceased's digital representation. Through selective input, ongoing interactive adjustments and imaginative cognitive supplementation, they build an idealized digital figure blending authentic memories with personal expectations. Deadbots provide a private space to grieve without social pressure and a channel to address unresolved emotions. In this process, users' memory of the deceased evolves dynamically: from initial reinforcement and idealization to a later stage where AI-generated new memories blur with authentic recollections, reflecting a complex desire for connection through an artificial medium. This blurring raises ethical concerns regarding memory distortion and dependency, underscoring the need for future clinical research on the long-term impact of AI-mediated grieving.

cs.HC↗
arXiv2026

Using surface acoustic waves to drive thin film flow over an obstacle

We study a new paradigm for ultrasonic driven object coating by using a model system where MHz-level surface acoustic waves (SAWs) drive the spreading of a silicone oil film atop topographical obstacles. We use experiments to show that nanometer-amplitude SAWs, propagating in the substrate of a piezoelectric actuator, propel macroscopic oil films to climb and traverse solid obstacles placed on the actuator. The oil dynamics reveal rich coupling between ultrasonic forcing, capillarity, and gravity; the balance of which determines coating success. We formulate a simplified two-dimensional theoretical model that incorporates obstacle geometry directly in the oil thin-film evolution equation, introducing a new representation of acoustic streaming in the presence of substrate height variations. Despite the simplifications inherent in the modeling, simulations show qualitative agreement with the experiments, providing evidence that the model captures the key physics.

physics.flu-dyn↗
arXiv2026

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video world models pre-trained on web-scale video corpora exhibit robust spatiotemporal reasoning and accurate future prediction, making them a natural foundation for enhancing VLA learning. Therefore, we propose \textit{GigaBrain-0.5M*}, a VLA model trained via world model-based reinforcement learning. Built upon \textit{GigaBrain-0.5}, which is pre-trained on over 10,000 hours of robotic manipulation data, whose intermediate version currently ranks first on the international RoboChallenge benchmark. \textit{GigaBrain-0.5M*} further integrates world model-based reinforcement learning via \textit{RAMP} (Reinforcement leArning via world Model-conditioned Policy) to enable robust cross-task adaptation. Empirical results demonstrate that \textit{RAMP} achieves substantial performance gains over the RECAP baseline, yielding improvements of approximately 30\% on challenging tasks including \texttt{Laundry Folding}, \texttt{Box Packing}, and \texttt{Espresso Preparation}. Critically, \textit{GigaBrain-0.5M$^*$} exhibits reliable long-horizon execution, consistently accomplishing complex manipulation tasks without failure as validated by real-world deployment videos on our \href{https://gigabrain05m.github.io}{project page}.

cs.CV↗
arXiv2026

SALIENT: Frequency-Aware Paired Diffusion for Controllable Long-Tail CT Detection

Detection of rare lesions in whole-body CT is fundamentally limited by extreme class imbalance and low target-to-volume ratios, producing precision collapse despite high AUROC. Synthetic augmentation with diffusion models offers promise, yet pixel-space diffusion is computationally expensive, and existing mask-conditioned approaches lack controllable attribute-level regulation and paired supervision for accountable training. We introduce SALIENT, a mask-conditioned wavelet-domain diffusion framework that synthesizes paired lesion-masking volumes for controllable CT augmentation under long-tail regimes. Instead of denoising in pixel space, SALIENT performs structured diffusion over discrete wavelet coefficients, explicitly separating low-frequency brightness from high-frequency structural detail. Learnable frequency-aware objectives disentangle target and background attributes (structure, contrast, edge fidelity), enabling interpretable and stable optimization. A 3D VAE generates diverse volumetric lesion masks, and a semi-supervised teacher produces paired slice-level pseudo-labels for downstream mask-guided detection. SALIENT improves generative realism, as reflected by higher MS-SSIM (0.63 to 0.83) and lower FID (118.4 to 46.5). In a separate downstream evaluation, SALIENT-augmented training improves long-tail detection performance, yielding disproportionate AUPRC gains across low prevalences and target-to-volume ratios. Optimal synthetic ratios shift from 2x to 4x as labeled seed size decreases, indicating a seed-dependent augmentation regime under low-label conditions. SALIENT demonstrates that frequency-aware diffusion enables controllable, computationally efficient precision rescue in long-tail CT detection.

eess.IV↗
arXiv2026

fix pimd/langevin: An Efficient Implementation of Path Integral Molecular Dynamics in LAMMPS

Path integral molecular dynamics (PIMD), which maps a quantum particle onto a fictitious classical system of ring polymers and propagates the "beads" of this extended classical system using molecular dynamics, is widely used to capture nuclear quantum effects (NQEs) in molecular simulations. Accurate PIMD calculations typically require a large number of beads and are therefore computationally demanding. While software packages such as i-PI offer comprehensive PIMD functionality, the high efficiency of simulations driven by machine learning interatomic potentials, such as Deep Potential (DP), calls for more efficient PIMD implementations that fully exploit modern massively parallel supercomputers. Here we present fix pimd/langevin, an efficient PIMD implementation in LAMMPS that supports commonly used features and leverages the Message Passing Interface architecture of LAMMPS to achieve high computational efficiency. We demonstrate the usage and validate the correctness of our code using liquid water as a representative example, and provide a comprehensive overview of the supported features. Then we discuss several important technical aspects of the implementation. Using DP simulations of water as a benchmark, we show that our implementation achieves several-fold acceleration compared to i-PI. Finally, we report strong and weak scaling results that demonstrate the favorable parallel performance of our code.

physics.chem-ph↗
arXiv2026

Using wetting and ultrasonic waves to extract oil from oil/water mixtures

Oil and water placed atop of a solid surface respond differently to a MHz-level surface acoustic wave (SAW) propagating in the solid due to their different surface wetting properties. We observe that, under SAW excitation, oil films, whether non-organic silicon oil or organic sunflower oil, are extracted continuously from sessile drops, comprising emulsions of the oil in question in a solution of water and surfactants. The mechanism responsible for the extraction of oil from the mixtures is the acoustowetting phenomenon: the low surface tension oil phase leaves the mixture in the form of 'fingers' that, away from the drop, spread opposite the path of the SAW. The high surface tension water phase remains at rest. Increasing either the SAW intensity or the oil content in the mixture enhances the rate at which oil leaves the emulsion. We further observe acoustic-capillary flow instabilities at the free surface of the oil film and the formation of spatial gradients in the emulsion oil-concentrations in the presence of SAW. Our study suggests the potential for using SAW for heterogeneous removal of oil from oil-in-water mixtures to complement current phase separation methods.

physics.flu-dyn↗
arXiv2026

Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval

Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense, multi-scale semantics inherent in overhead imagery. Moreover, adapting these heavy models via full fine-tuning incurs prohibitive computational costs and risks catastrophic forgetting. To address these challenges, we propose MPS-CLIP, a parameter-efficient framework designed to shift the retrieval paradigm from global matching to keyword-guided fine-grained alignment. Specifically, we leverage a Large Language Model (LLM) to extract core semantic keywords, guiding the Segment Anything Model (SamGeo) to generate semantically relevant sub-perspectives. To efficiently adapt the frozen backbone, we introduce a Gated Global Attention (G^2A) adapter, which captures global context and long-range dependencies with minimal overhead. Furthermore, a Multi-Perspective Representation (MPR) module aggregates these local cues into robust multi-perspective embeddings. The framework is optimized via a hybrid objective combining multi-perspective contrastive and weighted triplet losses, which dynamically selects maximum-response perspectives to suppress noise and enforce precise semantic matching. Extensive experiments on the RSICD and RSITMD benchmarks demonstrate that MPS-CLIP achieves state-of-the-art performance with 35.18% and 48.40% mean Recall (mR), respectively, significantly outperforming full fine-tuning baselines and recent competitive methods. Code is available at https://github.com/Lcrucial1f/MPS-CLIP.

cs.CV↗
arXiv2026

Imaging supermoiré relaxation in helical trilayer graphene

In twisted van der Waals materials, local atomic relaxation can alter the underlying electronic structure. Characterizing lattice reconstruction and its susceptibility to strain is essential for understanding emergent electronic states, especially in multilayers in which interference between moiré lattices yields larger supermoiré patterns whose energy is highly sensitive to local stacking. Here we image spatial modulations in the electronic character of helical trilayer graphene, which indicate relaxation into a superstructure of large domains with uniform moiré periodicity. We show that the supermoiré domain size is increased by strain and can be altered in the same device while preserving the local properties within each domain. Finally, we observe a higher conductance at the domain boundaries, consistent with predictions that they host counter-propagating edge modes. Our work provides a real-space visualization of moiré-periodic domains, reveals two independently tunable length scales and demonstrates strain engineering as a route towards designing correlated topological networks at the supermoiré scale.

cond-mat.mes-hall↗
arXiv2026

Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning

Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation of continuous frames. While these models show promise for Generative Video Reasoning (GVR), existing evaluation frameworks often rely on single-frame assessments, which can lead to outcome-hacking, where a model reaches a correct conclusion through an erroneous process. To address this, we propose a process-aware evaluation paradigm. We introduce VIPER, a comprehensive benchmark spanning 16 tasks across temporal, structural, symbolic, spatial, physics, and planning reasoning. Furthermore, we propose Process-outcome Consistency (POC@r), a new metric that utilizes VLM-as-Judge with a hierarchical rubric to evaluate both the validity of the intermediate steps and the final result. Our experiments reveal that state-of-the-art video models achieve POC@1.0 only about 20% and exhibit a significant outcome-hacking. We further explore the impact of test-time scaling and sampling robustness, highlighting a substantial gap between current video generation and true generalized visual reasoning. Our benchmark are released at https://github.com/RUCAIBox/VIPER.

cs.CV↗
arXiv2026

Narrowband four-photon states from spontaneous four-wave mixing

We observe time-correlated four photons within a correlation window of 20ns from spontaneous four-wave mixing via a double-Lambda scheme in a cold cloud of Rb-87 atoms. In contrast to high-power pulsed pumping of chi^(2) nonlinear processes in crystals, our scheme generates correlated four-photon states by direct continuous-wave pumping at nominal powers. We verify the presence of genuinely correlated four-photon states over accidentals by higher-order intensity cross-correlation measurements and accidental subtraction. We infer a time-correlated four-photon generation rate of 2.5(4)x10^6 counts per second close to saturation. The photons produced are near-resonant with atomic transitions, and have a bandwidth in the order of MHz, making them readily compatible with quantum networking applications involving atoms.

quant-ph↗
arXiv2026

KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures

To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that guides knowledge graph exploration. This module is embedded as executable code within the reasoning prompt, allowing the model to leverage external structured knowledge during inference. Based on this design, we develop an enhanced distillation-based reasoning framework that explicitly regulates intermediate reasoning steps, resulting in more reliable predictions. We evaluate the proposed approach on multiple public benchmarks using GPT-4 and LLaMA-3.3. Experimental results show that code-guided reasoning significantly improves contextual modeling and reduces prompt-induced hallucinations. Specifically, HIT@1, HIT@3, and HIT@5 increase by 15.64%, 13.38%, and 13.28%, respectively, with scores exceeding 95% across several evaluation settings. These findings indicate that the proposed method effectively constrains erroneous reasoning while improving both accuracy and interpretability.

cs.CL↗
arXiv2026

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide knowledge-graph exploration and incorporate code as part of the chain-of-thought prompt, forming an external knowledge input that provides more accurate and structured information to the model. Based on this design, we develop an improved knowledge distillation chain-style model and leverage it to analyze and constrain the reasoning process of LLMs, thereby improving inference accuracy. We empirically evaluate the proposed approach using GPT-4 and LLaMA-3.3 on multiple public datasets. Experimental results demonstrate that incorporating code modules significantly enhances the model's ability to capture contextual information and effectively mitigates prompt-induced hallucinations. Specifically, HIT@1, HIT@3, and HIT@5 improve by 15.64%, 13.38%, and 13.28%, respectively. Moreover, the proposed method achieves HIT@1, HIT@3, and HIT@5 scores exceeding 95% across several evaluation settings. These results indicate that the proposed approach substantially reduces hallucination behavior while improving the accuracy and verifiability of large language models.

cs.CL↗
arXiv2025

Assessment of First-Principles Methods in Modeling the Melting Properties of Water

First-principles simulations have played a crucial role in deepening our understanding of the thermodynamic properties of water, and machine learning potentials (MLPs) trained on these first-principles data widen the range of accessible properties. However, the capabilities of different first-principles methods are not yet fully understood due to the lack of systematic benchmarks, the underestimation of the uncertainties introduced by MLPs, and the neglect of nuclear quantum effects (NQEs). Here, we systematically assess first-principles methods by calculating key melting properties using path integral molecular dynamics (PIMD) driven by Deep Potential (DP) models trained on data from density functional theory (DFT) with SCAN, revPBE0-D3, SCAN0 and revPBE-D3 functionals, as well as from the MB-pol potential. We find that MB-pol is in qualitatively good agreement with the experiment in all properties tested, whereas the four DFT functionals incorrectly predict that NQEs increase the melting temperature. SCAN and SCAN0 slightly underestimate the density change between water and ice upon melting, but revPBE-D3 and revPBE0-D3 severely underestimate it. Moreover, SCAN and SCAN0 correctly predict that the maximum liquid density occurs at a temperature higher than the melting point, while revPBE-D3 and revPBE0-D3 predict the opposite behavior. Our results highlight limitations in widely used first-principles methods and call for a reassessment of their predictive power in aqueous systems.

physics.chem-ph↗
arXiv2025

HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation

We present HY-Motion 1.0, a series of state-of-the-art, large-scale, motion generation models capable of generating 3D human motions from textual descriptions. HY-Motion 1.0 represents the first successful attempt to scale up Diffusion Transformer (DiT)-based flow matching models to the billion-parameter scale within the motion generation domain, delivering instruction-following capabilities that significantly outperform current open-source benchmarks. Uniquely, we introduce a comprehensive, full-stage training paradigm -- including large-scale pretraining on over 3,000 hours of motion data, high-quality fine-tuning on 400 hours of curated data, and reinforcement learning from both human feedback and reward models -- to ensure precise alignment with the text instruction and high motion quality. This framework is supported by our meticulous data processing pipeline, which performs rigorous motion cleaning and captioning. Consequently, our model achieves the most extensive coverage, spanning over 200 motion categories across 6 major classes. We release HY-Motion 1.0 to the open-source community to foster future research and accelerate the transition of 3D human motion generation models towards commercial maturity.

cs.CV↗