arXiv subjects

Yifan Li

Publications and source records attributed to Yifan Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

cboamd: A Machine Learning Molecular Dynamics Framework for Vibrational Strong Coupling

Under vibrational strong coupling (VSC), molecular vibrations hybridize with an optical cavity mode to form polaritons, offering a route to modify chemical and material properties without external driving. In this work, we develop a machine-learning interatomic potential (MLIP) based framework to study VSC inside optical cavities. By using the cavity Born-Oppenheimer approximation and treating the photonic degrees of freedom as an effective electric field, we provide a framework that can describe VSC solely based on the electronic ground-state potential energy surfaces (PES), electronic dipole moment, and polarizability, all quantities obtained outside the cavity. We train PES, polarization, and polarizability models to drive the molecular dynamics (MD) simulations of systems under VSC. We demonstrate the approach for both a single CO$_2$ molecule and liquid CO$_2$, showing that the polarizability renormalizes the effective cavity resonance: at fixed cavity frequency this renormalization renders the Rabi splitting strongly asymmetric, while with renormalized cavity frequency the symmetric splitting is capped by polarizability screening. The collective Rabi splitting of the liquid is connected quantitatively to the single-molecule splitting involving the $\sqrt{N/3}$ orientational enhancement and the local-field enhanced effective charges of the coupled vibration, while the equilibrium pair structure of the CO$_2$ liquid remains unchanged. These simulations are the first MLIP-driven simulations of collective VSC in the condensed phase and open further pathways to the exploration of chemical effects under VSC.

physics.chem-ph↗

arXiv2026

Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation

Language instructions offer a flexible way to specify task semantics but can become ambiguous in cluttered scenes containing multiple visually similar objects and candidate targets. We study Spatially Prompted Visual Trajectory Prediction (SP-VTP), an open-loop setting in which points or bounding boxes in the first egocentric frame specify an object--target pair and condition the prediction of future 3D end-effector (EE) trajectory chunks. To support this setting, we introduce EgoSPT, a controlled dataset comprising 2,841 egocentric fork pick-and-place episodes with first-frame object and target annotations and reconstructed 3D EE trajectories. SP-VTP evaluates whether a static task specification remains informative as the viewpoint and scene configuration evolve throughout execution. We also introduce SPOT, a spatially prompted object--target trajectory predictor that integrates first-frame visual and coordinate prompts with current visual observations and motion history to generate future trajectories. Rather than relying on an explicit object tracker, SPOT maintains a fixed representation of the first-frame task specification. Across three training seeds, spatial prompting consistently reduces translation and endpoint errors relative to a no-prompt baseline, while controlled prompt interventions reveal distinct roles for object and target cues at different stages of execution. Together, EgoSPT and SPOT provide a dataset and baseline for spatially conditioned egocentric trajectory prediction in open-loop pick-and-place settings.

cs.CV↗

arXiv2026

Machine learning for the design and prediction of soft-magnetic electromagnetic shielding FeCo-based alloys in laser cladding

Electromagnetic shielding materials play a pivotal role in both aerospace applications and daily life. However, their design and manufacturing still face persistent challenges. Machine learning demonstrates significant potential in accelerating material development and compositions optimization. Furthermore, laser additive manufacturing provides powerful technical support for fabricating multi-component, multifunctional electromagnetic shielding materials with tailored properties. In this study, the multiple machine learning strategies have been proposed, based on experimental derivation and soft magnetic material databases, to accelerate the design of multifunctional FeCo-based alloys for electromagnetic interference (EMI) shielding within an almost infinite compositional space. This work presents a novel approach for the rapid and automated discovery of multifunctional alloys with optimized EMI shielding effectiveness, as well as enhanced magnetic and electrical properties.

cond-mat.mtrl-sci↗

arXiv2026

PeroMAS: A Multi-agent System of Perovskite Material Discovery

As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential. The development process of PSCs is precise and complex, involving a series of closed-loop workflows such as literature retrieval, data integration, experimental design, and synthesis. However, existing AI perovskite approaches focus predominantly on discrete models, including material design, process optimization,and property prediction. These models fail to propagate physical constraints across the workflow, hindering end-to-end optimization. In this paper, we propose a multi-agent system for perovskite material discovery, named PeroMAS. We first encapsulated a series of perovskite-specific tools into Model Context Protocols (MCPs). By planning and invoking these tools, PeroMAS can design perovskite materials under multi-objective constraints, covering the entire process from literature retrieval and data extraction to property prediction and mechanism analysis. Furthermore, we construct an evaluation benchmark by perovskite human experts to assess this multi-agent system. Results demonstrate that, compared to single Large Language Model (LLM) or traditional search strategies, our system significantly enhances discovery efficiency. It successfully identified candidate materials satisfying multi-objective constraints. Notably, we verify PeroMAS's effectiveness in the physical world through real synthesis experiments.

cs.MA↗

arXiv2026

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify nodes. We study a hybrid distance-spectral encoding that combines anchor-distance profiles with quantized low-frequency Laplacian-energy coordinates. Treating the encoding as an observation map yields a simplex-refined converse, an exact collision factorization $κ_H=κ_Dκ_{S|D}$, and the collision information $I_H=-\logκ_D-\logκ_{S|D}$. On random regular graphs, the criterion is made explicit through a bounded-correlation Gaussian-wave surrogate; for actual Laplacian-energy coordinates, we give the distance-conditioned spectral collision condition sufficient for conditional actual-coordinate achievability. Experiments show that $I_H/\log n$ calibrates localization success, and PE-only structural task probes on Universal Dependencies trees show that hybrid encodings better recover syntactic-tree geometry than distance-only or spectral-only baselines.

cs.LG↗

arXiv2026

Kempe factorizations for rational curves on $\operatorname{SO}_4(\mathbb{R})$

We study constructive Kempe factorizations for rational curves on $\operatorname{SO}_4(\mathbb{R})$. Motivated by motion-polynomial factorization and rational matrix curves on real classical groups, we prove that every rational curve of degree $2d$ with $d\ge1$ first factors into $d$ quadratic rational curves and then into a product of at most $2d$ planar rotation curves, where each planar rotation curve fixes a two-dimensional plane pointwise. The construction proceeds by extracting left and right isoclinic polynomial parts via Cayley's factorization, factoring the corresponding quaternion polynomials, and pairing linear factors with equal norm polynomials. The resulting algorithms are explicit and are illustrated by examples.

math.AG↗

arXiv2026

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation

Robotic manipulation requires models that generate executable actions while anticipating and evaluating their future consequences before physical execution. We present $τ_0$-World Model ($τ_0$-WM), a unified video-action world model that integrates policy learning, video prediction, and action evaluation within a single future-predictive framework. Built on a shared video diffusion backbone, $τ_0$-WM provides two complementary interfaces. First, a video action model jointly predicts future visual latents and continuous action chunks from multi-view observations, language instructions, and robot state. Second, an action-conditioned video simulator rolls out candidate action chunks into multi-view futures and predicts dense task-progress scores. The model is trained on approximately $27{,}300$ hours of real-robot teleoperation, UMI-style interaction, egocentric human videos, and rollout or failure trajectories using modality-specific supervision masks. At inference time, $τ_0$-WM uses test-time computation to sample action candidates, rank them with re-denoising consistency, and invoke simulator-based rectification for low-quality candidates. On challenging long-horizon and fine-grained robotic manipulation tasks, $τ_0$-WM shows superior performance over other relevant baselines.

cs.RO↗

arXiv2026

$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $τ_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

cs.RO↗

arXiv2026

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales pretraining to over 37,000 hours of heterogeneous embodied data, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation. Compared with the preceding GigaBrain-0 series and prior state-of-the-art models including $π_{0.5}$, GigaBrain-0.7 achieves substantial improvements in foundation zero-shot capabilities, language-conditioned instruction following, and post-training task success rates. In particular, on our in-house Maker H01 platform and mainstream robot embodiments, GigaBrain-0.7 demonstrates strong task adaptability and completion ability across both home and industrial scenarios. All training code and pretrained model weights will be released.

cs.RO↗

arXiv2026

Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples

Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples.

cs.LG↗

arXiv2026

StructReward: Efficient Structured Process Rewards for Self-Correcting Multimodal Reasoning

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning. However, most existing methods evaluate an entire response using a binary reward based only on final-answer correctness, thereby discarding the supervision available in intermediate reasoning steps. Process reward models offer finer-grained feedback, but they typically rely on separately trained verifiers, costly chain-of-thought annotations, or online judging by large language models (LLMs). In this work, we introduce StructReward, a compute-efficient framework that provides dense reinforcement signals through structured step-level reward alignment. StructReward represents each generated solution as a sequence of reasoning steps and aligns them with process-labeled reference steps using lightweight numerical, symbolic, and lexical matching rules. The aligned labels are aggregated into a dense process reward and combined with final-answer consistency and output-validity rewards through a gated Group Relative Policy Optimization (GRPO) objective. We further recycle policy rollouts into complementary supervision for response comparison and reflective self-correction, rather than discarding them after policy updates. Separately, we use a strong LLM to rewrite sampled correct trajectories into reflection-oriented training instances, further strengthening the policy's ability to evaluate and refine its reasoning. Since reward computation is performed online without an additional learned verifier or external LLM judge, StructReward substantially reduces the computational overhead of multimodal reinforcement learning. Experimental results show that structured process supervision and rollout recycling provide an efficient path toward self-improving multimodal reasoning.

cs.AI↗

arXiv2026

What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills

Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear. We study skill valuation: assigning credit to the internal units of a fixed skill, such as rules, examples, scripts, and heuristics, under a fixed agent and held-out task distribution. Skill valuation differs from data or prompt-span valuation because skill units are structured: they may depend on other units, belong to a document hierarchy, trigger agent behavior, and consume limited prompt context. We introduce SkillSV, a structure-aware Shapley-style framework for skill valuation. SkillSV compiles a skill into units, dependencies, and hierarchy, so that only valid counterfactual skills are evaluated. It uses paired deletion and length-neutral padding to separate content value from context cost, and estimates the resulting values with a rollout-budgeted estimator for noisy agent evaluations. On four agentic benchmarks, we assess the faithfulness, actionability, and explanation of SkillSV: it recovers unit interactions, preserves aggregate skill lift, and guides safe pruning and compression.

cs.AI↗

arXiv2026

Optimal Measurement of Drone Swarm in RSS-based Passive Localization with Region Constraints

Passive geolocation by multiple unmanned aerial vehicles (UAVs) covers a wide range of military and civilian applications including rescue, wild life tracking and electronic warfare. The sensor-target geometry is known to significantly affect the localization precision. The existing sensor placement strategies mainly work on the cases without any constraints on the sensors locations. However, UAVs cannot fly/hover simply in arbitrary region due to realistic constraints, such as the geographical limitations, the security issues, and the max flying speed. In this paper, optimal geometrical configurations of UAVs in received signal strength (RSS)-based localization under region constraints are investigated. Employing the D-optimal criteria, i.e., minimizing the determinate of Fisher information matrix (FIM), such optimal problem is formulated. Based on the rigorous algebra and geometrical derivations, optimal and also closed form configurations of UAVs under different flying states are proposed. Finally, the effectiveness and practicality of the proposed configurations are demonstrated by simulation examples.

eess.SP↗

arXiv2026

AttnLink: Turning Attention into Schema Links for Text-to-SQL

Schema linking is a critical component of Text-to-SQL systems, but existing approaches often trade off contextual modeling capacity, score-based controllability, and inference efficiency. We introduce AttnLink, an attention-based framework that converts LLMs' internal attention into continuous relevance scores for schema items. AttnLink extracts the attention from the generation-start position to candidate schema spans, enabling all candidates to be ranked in a single prefill pass without autoregressive decoding. We develop two variants: AttnLink-U, which directly probes pretrained attention without parameter updates, and AttnLink-S, which aligns the attention distribution with gold schema items through direct supervision. To improve coverage of multiple relevant schema items, AttnLink-S combines a set-mass objective with an adaptive probability-floor regularizer. The resulting scores support post-hoc precision-recall control through temperature scaling and cumulative-mass selection. Experiments on Spider, BIRD, and Spider2-SQLite show that AttnLink-S achieves mAP scores of 99.22%, 95.95%, and 83.29%, respectively, with millisecond-scale schema-linking latency. It also yields the best or tied-best execution accuracy for downstream SQL generation in seven of nine generator-dataset settings.

cs.CL↗

arXiv2026

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development

Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but often suffers from sparse rewards and cold-start failures when base large language models (LLMs) lack sufficient reasoning capability. Meanwhile, existing data synthesis methods mainly generate post-hoc rationales rather than executable environment-interaction trajectories. In this paper, we propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development. EviPath reverse-engineers executable trajectories from question-answer pairs and supporting evidence through three stages: (i) Abductive Subtask Planning, which decomposes questions and plans dependency-aware solution paths; (ii) Faithful Sub-question Answering, which uses supporting evidence as a proxy environment to generate grounded intermediate thoughts and answers; and (iii) Conversational Fine-Tuning, which converts complete trajectories into a dialogue format for supervised fine-tuning. Experiments on widely used question-answering benchmarks show that an 8B model trained on our synthetic corpus significantly and consistently outperforms state-of-the-art baselines, achieving a 14.7% absolute Exact Match gain in open-domain question answering.

cs.CL↗

arXiv2026

Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels

Direct Preference Optimization (DPO) has become an important method for aligning large language models (LLMs) with human preferences because it removes the need for explicit reward modeling and reinforcement learning. However, its performance depends heavily on the quality of preference data, and noisy preference data in real-world settings can weaken alignment performance. To address this issue, we propose a bilevel optimization framework and prove, under some idealized conditions, that this framework can recover the DPO optimum under clean data. We further derive a prior form for the learnable weighting function under label-flipping noise. Considering that high-quality metadata may be difficult to obtain, we propose a prompt augmentation consistency method that enables meta-learning even when metadata is completely unavailable. To reduce the high cost of higher-order gradients in LLM meta-learning, we combine central-difference approximation with LoRA fine-tuning and develop a scalable training scheme. Experiments on TL;DR summarization and Anthropic Helpful and Harmless dialogue show that the proposed method improves alignment performance over multiple DPO baselines under different noise rates.

cs.LG↗

arXiv2026

Link between thermodynamic correlation signatures and superconductivity in twisted trilayer graphene

Twisted graphene multilayers exhibit strong electronic correlations, which manifest in a range of experimental signatures. Yet how these signatures relate to each other and the microscopic ground states-and how twist angle and band structure reshape them-remains poorly understood. Here we study this interplay by correlating local thermodynamic and transport measurements in a twisted trilayer graphene (TTG) sample with unequal angles and flat electronic bands. We use a scanning single-electron transistor to map the impact of electron-electron interactions in a region of the sample where the local twist angle evolves smoothly. We observe gapped correlated insulators and a sawtooth in electronic compressibility, both exhibiting pronounced electron-hole (e-h) asymmetry with distinct magic angles for conduction and valence bands. Subsequent transport measurements in the same region reveal robust superconductivity with a similar e-h asymmetry. Our measurements indicate that superconductivity is not directly tied to the correlated insulators. Instead, its critical temperature correlates closely with the strength of the sawtooth in compressibility, suggesting a common origin or link between the two. By combining a local probe with transport measurements, we uncover connections between superconductivity and thermodynamic correlation signatures that are not apparent from either technique in isolation, highlighting the power of our dual approach and establishing their dependence on interlayer twist angles in TTG.

cond-mat.mes-hall↗

arXiv2026

picoRing dual: ultralow-power bimanual ring controllers for everyday AR

Advances in smart eyewear, such as AR glasses and HMDs, bring digital information into outdoor and public situations. However, traditional handheld controllers for hand interactions remain too bulky and socially awkward for these everyday contexts, failing to match the portability and subtlety required for mobile use. Ring-based input controllers offer a reliable finger-sensing solution; however, continuous operation with a tiny, battery-constrained ring remains challenging. Here, we present picoRing dual, an ultra-low-power bimanual interface with a pair of ring-wristbands based on inductive coupling. Unlike the original picoRing mouse limited to uni-manual tens of bps slow trackball interaction, picoRing dual uses a stable NFC-based ring-to-wristband link to capture fast index-finger motions and thumb-to-index microgestures at approximately 1.4 kbps. By tuning the ring's coil geometry, our system achieves stable NFC against finger bending while complying with NFC's ultra-low power profile. Therefore, picoRing dual with approximately 0.86 mW on the ring side can last approximately 100 continuous hours on a single charge of the ring's 20 mAh battery. picoRing dual has the potential to offer ubiquitous finger input for everyday AR interaction.

cs.HC↗