arXiv subjects

Yifan Li

Publications and source records attributed to Yifan Li.

At least 19 recordsLinked to original sources

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

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 $\kappa_H=\kappa_D\kappa_{S|D}$, and the collision information $I_H=-\log\kappa_D-\log\kappa_{S|D}$. 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

Cheaper by the Batch: Shared Traversal for Genotype Graph Editing

Updating a graph by inserting or replacing nodes while preserving semantics and reusing existing structure is a recurring computational problem. In population genetics, this problem arises in the genotype representation graph (GRG), a directed acyclic graph that losslessly encodes phased genetic variation across hundreds of thousands of samples by sharing subgraph structure for individual mutations. In a GRG, each mutation's carrier set is implicitly encoded as the set of leaf nodes reachable from the node it is assigned to. Updating a mutation is therefore a structural editing problem, and current approaches remap mutations individually. This paper introduces a batched mutation-remapping algorithm that replaces independent reuse-aware traversals with a single shared reverse-topological pass, identifying reuse candidates for an entire batch at once. The pass propagates compact bit-parallel per-mutation state and uses an adaptive sparse/dense carrier set representation spanning rare-to-common variant densities. Batching is the memory-scalable complement to split-based parallelism, which instead replicates graph and traversal state per worker. Our remapping is evaluated on a controlled update workload and on end-to-end allele polarization, a bulk carrier set update that is common in population genetic analysis. Our approach is up to 10.5$\times$ faster than independent remapping while preserving exact carrier-set semantics.

cs.DS↗

arXiv2026

$\tau_0$-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 $\tau_0$-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 $\pi_{0.5}$, 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

SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning

Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness only as a trajectory-level reward, which provides limited guidance for identifying the SQL decisions responsible for success or failure. We propose SERL-SQL, a selective execution-grounded reinforcement learning framework for multi-turn Text-to-SQL agents. SERL-SQL samples on-policy SQL interaction trajectories and uses a training-only teacher to re-score student actions with execution feedback. The resulting teacher--student likelihood gap is converted into bounded, masked weights that reweight GRPO advantages only on SQL and tool-action tokens. In this way, task rewards preserve the optimization direction, while execution hindsight provides localized credit assignment. Experiments on BIRD, Spider, and cross-domain benchmarks show that SERL-SQL achieves competitive performance, reaching 76.56% execution accuracy on BIRD-Dev and 89.92% on Spider-Test. Moreover, our reward-based selection strategy closely approaches the oracle Best-of-N upper bound and consistently outperforms consistency-based selection, showing that SERL-SQL produces high-quality candidates that can be reliably identified by lightweight execution-grounded rewards. Our code will be released at https://github.com/Ffunkytao/SERL-SQL.

cs.CL↗

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

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerged as a powerful paradigm for eliciting chain-of-thought reasoning. However, due to computational constraints, existing studies are largely restricted to small models, leaving the training dynamics and emergent capabilities at a large scale unexplored. To meaningfully explore this frontier, we aim to elicit high-quality reasoning behaviors from the model. However, we find that naive scaling often suffers from poor readability, token redundancy, and a lack of adaptive reasoning depth. To address these challenges, we present a stable and efficient training pipeline, incorporating algorithmic and system optimizations such as clipped importance sampling, training-inference ratio correction, and mixed-precision control. Our experiments offer three key findings that validate the "bitter lesson" of scaling: (1) scaling to 1T parameters significantly enhances sample efficiency and performance ceilings; (2) the training process progresses sequentially through an initial discovery phase followed by a sharpening phase; and (3) the model spontaneously develops advanced cognitive behaviors, including anthropomorphism, structured formatting, self-verification, parallel reasoning, and context anxiety, rendering hand-crafted heuristics redundant. Evaluated on seven mathematical benchmarks, Ring-2.5-1T-Zero achieves competitive performance. Additionally, to assess CoT quality beyond final-answer correctness, we propose a structured evaluation framework across three dimensions: comprehensibility, reproducibility, and efficiency, where our model demonstrates clear advantages in producing structured and concise reasoning traces. By sharing our observed emergent phenomena, we hope to provide the community with deeper insights into scaling behaviors, particularly at the 1-trillion scale.

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

dpti: An Automated Thermodynamic Integration Workflow for Phase Diagram Calculations with Machine Learning Interatomic Potentials

Thermodynamic integration (TI) is a widely used approach for computing free energies and phase diagrams. However, TI calculations driven by machine learning interatomic potentials (MLIPs) remain technically challenging because they require careful design of reversible integration paths and many closely related molecular dynamics (MD) tasks for each phase and state point. To address these challenges, we present dpti, an open-source Python package that automates TI workflows for phase diagram calculations with MLIPs. dpti connects reference systems with analytically known free energies to MLIP-described atomic and molecular solids and liquids through reversible integration paths. Given JSON input files, dpti generates and runs the required MD tasks, computes free energy contributions, estimates errors, and propagates coexistence points into phase boundaries. We demonstrate the usage of dpti with two examples driven by Deep Potential models: a silica phase diagram involving beta-quartz, coesite, and melt, and the ice Ih-liquid water phase boundary. dpti provides a useful tool for automated phase diagram calculations of materials modeled by MLIPs.

physics.comp-ph↗

arXiv2026

FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.

cs.CL↗

arXiv2026

Machine-knittable, Magnetically-Plug-n-Play E-Textile Prototyping

Electronic textiles (e-textiles) integrated with wearable sensors are essential for daily motion monitoring and long-term physiological sensing. For example, capturing optimal kinematic or bio-signals requires aligning sensors with specific anatomical parts, which vary significantly across individuals and application scenarios. This necessity for personalization makes e-textile prototyping inherently iterative, however current fabrication methods, such as manual conductive stitching, rely on permanent bonds that restrict rapid adjustment. This paper introduces Plug-n-play e-knit, a machine-knittable e-textile prototyping platform that enables repeatable, quick adjustment of sensor positions across garments. First, to cover the large area of the textile for prototyping, we use industrial digital knitting of conductive yarn to integrate power and communication buses directly into the large-scale textile. Then, to ensure plug-n-play attachment to the textile, we employ soft-magnetic connectors that enable sensors to be repeatedly plugged into the wiring without damaging the fabric. Furthermore, our LED-positioning system enables the automatic identification and localization of each sensor node. We demonstrate the platform's capabilities through forearm movement calibration and position-aware temperature mapping.

cs.HC↗

arXiv2026

From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents

The integration of external tools has transitioned LLM agents from passive responders to autonomous systems. However, current benchmarks prioritize execution success, neglecting self-awareness capability, the ability to discern whether a problem requires necessary external resources or can be solved via internal parametric knowledge. To address this, we introduce KAPRO (Knowing-Acting Quadrant PRObe), a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting). We further construct KAware, a dataset rigorously partitioning tasks into external, internal, and hybrid subspaces to systematically probe these epistemic boundaries. Extensive experiments across diverse agent architectures show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings. Moreover, open-source and instruction-following models exhibit stronger tool overuse due to shallow pattern matching, while proprietary and reasoning-oriented models demonstrate more reliable cognitive gating. Benchmark and codes are available at https://github.com/AI-Santiago/KAware.

cs.AI↗

arXiv2026

Generative Archetype-Grounded Item Representations for Sequential Recommendation

Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic representations, existing approaches only rely on static encoding of fixed attributes, overlooking the crucial role of target audiences in defining item identity. Moreover, the semantic space struggles to reflect actual user behavior, resulting in a significant gap between semantic representations and behavioral patterns. To address these limitations, we propose GenAIR, a general framework that empowers sequential recommendation with Generative Archetype-grounded Item Representations. Specifically, we first leverage an LLM to analyze item metadata and infer textual description of the Archetype, which represents the conceptual profile of the item's ideal target audience. We then extract the corresponding embeddings in a single forward pass. Further, to ground these generative archetypes in real-world behavior, we introduce a behavioral calibration objective, which explicitly incorporates behavioral signals from actual interactions. This objective adjusts the structure of the embedding space to reflect empirical patterns. GenAIR enables seamless integration with most existing models while maintaining high efficiency. Comprehensive experiments conducted on three real-world datasets demonstrate that GenAIR significantly improves the performance of various sequential recommendation models and consistently outperforms state-of-the-art baseline approaches. Implementation codes are available at https://github.com/AI-Santiago/GenAIR.

cs.IR↗