Searcharxiv⌕ Search

arXiv subjects

Yu-Feng Li

Publications and source records attributed to Yu-Feng Li.

At least 19 recordsLinked to original sources

Robust Long-Tailed Learning under Label Noise

Long-tailed learning aims to enhance the generalization performance of underrepresented tail classes. However, previous methods have largely overlooked the prevalence of noisy labels in training data. In this paper, we address the challenge of noisy labels in long-tailed learning. We identify a critical issue: the commonly used small-loss noisy label detection criterion fails to perform effectively in long-tailed class distributions. This failure arises from the inherent bias of deep neural networks, which tend to misclassify tail class examples as head classes, leading to unreliable loss calculations. To mitigate this, we propose a novel small-distance criterion that leverages the robustness of learned representations, enabling more accurate identification of correctly-labeled examples across both head and tail classes. Additionally, to improve training for tail classes, we replace discrete pseudo-labels with label distributions for examples flagged as noisy, resulting in significant performance gains. Based on these contributions, we introduce the Robust Long-Tail learning framework, designed to train models that are resilient to both class imbalance and noisy labels. Extensive experiments on benchmark and real-world datasets demonstrate that our approach outperforms previous methods, offering substantial performance improvements.

cs.LG↗

Information-Theoretic Gaps in Solar and Reactor Neutrino Oscillation Measurements

Quantum estimation theory provides a fundamental framework for analyzing how precisely physical parameters can be estimated from measurements. Neutrino oscillations are characterized by a set of parameters inferred from experiments conducted in different production and detection environments. The two solar oscillation parameters, $Δm^2_{21}$ and $θ_{12}$, can be estimated using both solar neutrino experiments and reactor neutrino experiments. In this letter, we use Quantum Fisher Information (QFI) to quantify and compare the information content accessible in these two experimental setups. For reactor neutrinos, flavor measurements saturate the QFI for both parameters over relevant energy ranges, demonstrating that ideal measurements could achieve ultimate quantum precision bound. In contrast, for solar neutrinos the phase-based QFI vanishes, originating from the quantum coherence, rendering the estimation of $Δm_{21}^2$ purely population-based and effectively classical, while the QFI for $θ_{12}$ remains sizable and nearly saturated by flavor measurements at high energies. Consequently, solar experiments are intrinsically more sensitive to $θ_{12}$ than to $Δm_{21}^2$, reflecting a fundamental difference in the information encoded in the two systems.

hep-ph↗

ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

DeepSeek Sparse Attention (DSA) reduces the computational cost of attention through token-level selection. However, its indexer still scores the entire causal prefix for each query, making indexing a dominant source of latency in long-context inference. Notably, the indexer alone can account for more than 50% of total prefill GPU time at long context lengths. To address this bottleneck, we propose ADIndex, an Adaptive and Distillation-driven Indexing method for token-level sparse attention. ADIndex integrates three key components: (i) a layer-wise calibration strategy that adaptively accommodates cross-query retrieval overlap, motivated by our observation of pronounced inter-layer heterogeneity; (ii) a group-level distillation scheme that leverages this heterogeneity to efficiently train adaptive layer-wise group indexers, capturing salient retrieval signals from individual queries; and (iii) a low-latency inference strategy that reduces repeated full-prefix scans through token bank sharing within query groups while retaining query-specific refinement. Experiments on DeepSeek-V3.2 and GLM-5.1 demonstrate that ADIndex preserves near-lossless task performance on LongBench, LongBench v2, and RULER while delivering substantial efficiency gains over standard DSA, including prefill and decoding kernel speedups of up to 6.22x and 3.40x, respectively, at a context length of 256K across the layer-wise reuse configurations, as well as an end-to-end serving speedup of 1.54x at a context length of 128K.

cs.LG↗

Leptonic CP Phase Determination from Fisher Information in T2K and NO$ν$A

The precise determination of the leptonic CP phase $δ_{\rm CP}$ remains one of the central objectives of current and future long-baseline (LBL) neutrino oscillation experiments. Quantum estimation theory provides a natural framework to quantify the ultimate precision limits for estimating physical parameters encoded in quantum states. In this work, we employ the quantum Fisher information to investigate how much information about $δ_{\rm CP}$ is intrinsically encoded in neutrino states and how efficiently it is extracted in present LBL experiments such as T2K and NO$ν$A. We first analyze the intrinsic quantum sensitivity of neutrino and antineutrino states and demonstrate how matter effects generate a neutrino mass-ordering dependent information structure. To compare the intrinsic information content of the quantum state with the information experimentally accessible through flavor measurements, we compute the event-level Fisher information from reconstructed event spectra using Poisson statistics including backgrounds and systematics. We find that both experiments extract only a small fraction of the total information available in the underlying quantum state. This extraction efficiency becomes particularly suppressed near maximally CP-violating regions, where the reconstructed event spectra exhibit reduced sensitivity to small variations in $δ_{\rm CP}$. We also apply the same framework to the reactor mixing angle $θ_{13}$, providing a benchmark for comparison with the estimation of $δ_{\rm CP}$. Our analysis provides a complementary information-theoretic perspective on precise estimation of oscillation parameters in LBL neutrino experiments.

hep-ph↗

Boosted Dark Matter Directionality in Large Liquid Scintillator Detectors

Light dark matter can be boosted by cosmic-ray-dark matter interactions, which opens the possibility of direct-detection searches with large neutrino detectors. We consider the signal produced by boosted dark matter undergoing quasi-elastic scattering off carbon and knocking out a neutron in a large liquid scintillator detector. A distinctive delayed gamma ray from neutron capture can be reconstructed after $\sim 210$ $μ$s, which is paired up with the prompt signal during neutron propagation. We find that 100 kt$\cdot$yr of data from the neutron-coincidence channel will be able to probe new parameter space compared to free proton signals found in previous work. We further consider the possibility of utilizing directional information from the displaced vertex associated with the capture of the final-state neutron. However, we find that directional information does not materially improve the sensitivity due to the large nucleon scattering angle.

hep-ph↗

SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents

Skill learning enables web agents to reuse prior experience for long-horizon interactive tasks. However, learned skills are typically evaluated in closed environments, overlooking the fact that real-world web deployment involves continuous shifts in invocation context, perceptual grounding, and execution feasibility. To this end, we introduce SkillShift-Bench, the first benchmark for evaluating skill learning with controlled open-environment shifts. SkillShift-Bench simulates Contextual Shift, Perceptual Shift, and Execution Shift across three self-hosted web systems, and evaluates agents with diagnostics covering task success, interaction cost, skill use, and skill failure. Comprehensive experiments reveal systematic robustness degradation under controlled shifts, characterized by lower success rates, higher interaction costs, and more frequent skill failures, with Execution Shift exerting the strongest pressure. We further formulate shifted skill execution as a nonstationary local executability problem and provide both a dynamic-regret analysis and a practical test-time adaptation method, demonstrating the feasibility of improving learned-skill execution without relearning the skill library. Code, tasks, environments, documentation, and the leaderboard are available at https://skillshift-bench.github.io/.

cs.AI↗

Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating their capabilities through dense token-level supervision on student-generated trajectories. However, domain routing only distinguishes the supervision sources for different domains; updates from all domains still act on shared parameters. When teachers differ substantially in response style and domain expertise, supervision that is effective in isolation may still lead to persistent gradient conflicts and capability degradation during joint optimization. To address this challenge, we propose Cross-Teacher Guarding for MOPD (Road MOPD), which introduces non-routed teachers as auxiliary cross-domain critics on the same student trajectories and coordinates multi-teacher supervision through token-level credit assignment and gradient updates. Specifically, cross-teacher-guided credit assignment uses teacher agreement to strengthen token-level corrections jointly supported by the teachers and attenuate conflicting signals; preventive multi-teacher gradient projection uses auxiliary gradients from the same trajectories to constrain potentially conflicting updates and adaptively controls projection strength to retain target-domain learning signals. In experiments, Road MOPD mitigates degradation in the disadvantaged domain, gains over 5 percentage points under high conflict, and improves overall performance in low-conflict and three-domain settings.

cs.AI↗

CompoWorld: Compositional Environment Scaling for General Agents

Automatically generated environments provide a scalable source of interaction data for training general agents. However, existing approaches mainly generate tasks within a single environment, while real-world workflows require agents to connect information and actions across multiple services. We introduce Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services. Coding agents turn tool specifications into verified services with typed states and shared interfaces, while a world model handles tools that cannot be reliably implemented. A random-walk procedure connects services through dependency graphs, enabling the generation and verification of tasks that require information to flow across services. Verified trajectories support supervised fine-tuning (SFT), while our Completion-Focused Rubric Reward guides reinforcement learning (RL) toward full task completion by emphasizing criteria with lower pass rates within each rollout group. We construct 448 services exposing 10,130 tools and use 3K SFT trajectories and 1K RL tasks to train Qwen3.6-35B-A3B. Experimental results show that CompoWorld improves on its backbone by 9.17 points on average across eight benchmarks. On AutomationBench, it surpasses frontier models such as Claude Opus 4.6 and leads all compared agent-specialized 35B-A3B models.

cs.AI↗

Theory of inverse beta decay for reactor antineutrinos

Inverse beta decay (IBD), $\overlineν_e p \to e^+ n \left( γ\right)$, is the main detection channel for reactor antineutrinos in water- and hydrocarbon-based detectors. As reactor antineutrino experiments now target sub-percent-level sensitivity to oscillation parameters, a precise theoretical description of IBD, including recoil, weak magnetism, nucleon structure, and radiative corrections, becomes essential. In this work, we give a detailed and precise calculation of the total and differential cross sections for radiative IBD, $\overlineν_e p \to e^+ n γ$. We use a heavy baryon chiral perturbation theory framework, systematically incorporating electroweak, electromagnetic, and strong-interaction corrections. We derive new analytic cross-section expressions, clarify the collinear structure of radiative corrections, and provide a systematic uncertainty analysis. We also discuss phenomenological applications for reactor antineutrino experiments, e.g., JUNO, and neutron decay. Our results enable sub-permille theoretical precision, supporting current and future experiments.

hep-ph↗

Quantifying Information Hierarchy for Neutrino Oscillation Parameters at JUNO

Since neutrinos are quantum systems inherently, the precision with which oscillation parameters can be estimated ultimately depends on how much information about these parameters is encoded in the neutrino state and how efficiently that information can be extracted through measurement. In this work, we quantify how information encoded in reactor antineutrino states flows through the measurement process to the events observed at the detector, using quantum and classical Fisher information. We establish the information ladder for JUNO, revealing that the loss of precision across different information levels is strongly parameter dependent. We demonstrate that the JUNO configuration approaches the optimal statistical limit for the oscillation parameters of the solar sector, while information on $θ_{13}$ and $Δm_{31}^{2}$ is significantly degraded by the measurement strategy and detector effects. Despite this information loss, the remaining information is sufficient for JUNO to achieve sub-percent precision on $Δm_{31}^{2}$ within six years.

hep-ph↗

LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory

Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been largely driven by Multimodal Large Language Models (MLLMs). Existing methods follow a next-step action prediction paradigm, supervising only the expert action, which requires a high quantity of data for training. They also rely on cognitive maps, accumulated historical frames, or external 3D tools to maintain states, leading to high computational and memory overhead. To realize resource efficiency VLN, we propose LookStep, a unified end-to-end framework that combines Language Centric Future State Modeling and Event Driven Rolling Memory that uses language labels to generate coarse-grained navigation progress and future states for each candidate action, while autonomously deciding whether to write each observation into a bounded rolling memory with a semantic role. We validate LookStep empirically. On VLN-CE tasks, LookStep outperforms existing methods under the same training settings, achieving a 49.7\% success rate on R2R-CE Val-Unseen with better memory efficiency and less data usage. Code and model is available at https://github.com/kunyang-YU/LookStep.

cs.CV↗

Characterizing Single-Signal Events from Atmospheric-Neutrino Neutral-Current Interactions in Large Liquid Scintillator Detectors

Neutral-current interactions of atmospheric neutrinos in large liquid scintillator detectors offer a new opportunity to study single-signal events (hereafter singles), characterized by a prompt energy deposition on the MeV-to-GeV scale and no identified delayed signal. In this work, we systematically investigate the model dependence of atmospheric-neutrino singles due to the primary neutrino-nucleus interaction, residual-nucleus de-excitation, and secondary interactions in the scintillator. Our results show that the dominant model dependence originates from the primary neutrino-nucleus interaction, especially for neutral-current processes on carbon, whereas de-excitation is essential for the singles selection yet leads to relatively small spectral variations among realistic models. Secondary-interaction effects are also subdominant overall. We further present the predicted event rates and prompt-energy spectra for neutral-current singles, along with the charged-current contribution. Separately, we estimate the low-energy contribution from elastic scattering of sub-\SI{100}{\MeV} atmospheric neutrinos on free protons. These results highlight the physics potential of current and future large liquid scintillator detectors, such as the Jiangmen Underground Neutrino Observatory, to study atmospheric-neutrino singles, probe neutrino-nucleus interaction models, and improve background estimates for rare-event searches.

hep-ex↗

SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data

Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient feature informativeness. Automated Feature Engineering (AutoFE) overcomes this by automating feature generation and selection, ensuring both model performance and operational efficiency. However, traditional AutoFE often yield features with poor interpretability because they rely on blind mathematical transformations, while large language models (LLM)-based AutoFE faces challenges in requiring costly multi-round iterations to generate high-utility features to effectively enhance model performance, compounded by inherent risks of bias and hallucination. In this paper, we combine symbolic regression with LLMs for feature engineering (SymboLLM-FE) to solve these challenges. We extract mathematically expressive formulas strongly correlated with the target via symbolic regression, which can enhance model performance, then refine them by LLMs with rich prior knowledge to ensure interpretability. Empirical results on six real-world datasets and four Kaggle competitions demonstrate that SymboLLM-FE outperforms existing AutoFE. SymboLLM-FE also addresses the dual challenges of poor interpretability and numerous iterations by employing a statistical prior-grounded LLM refinement mechanism and single-digit LLM calls.

cs.LG↗

Binary Hypothesis Testing: A Robust Framework Against the Look Elsewhere Effect

In particle physics, discovery claims conventionally require an observed significance exceeding $5σ$. However, the interpretation of a $5σ$ result depends critically on the testing procedure, namely whether the hypothesis is tested at a single pre-specified point in parameter space or by scanning over a range of possible signal locations. This distinction gives rise to the look-elsewhere effect, a concept that is widely used but often interpreted as a simple penalty for scanning. In this work, we reinterpret the look-elsewhere effect as a correction for procedural inconsistency arising when the null distribution is generated under one procedure while the test statistic is evaluated under another. Within the framework of hypothesis testing, we examine its implications and clarify the distinct roles of the look-elsewhere effect in binary and peak-search scenarios. In particular, we show that binary test is robust against the look-elsewhere effect, whereas peak searches require an explicit correction for the search over signal locations. Using a moderate trial factor of approximately 26, calibrated from the ATLAS Higgs search, we show that a $3σ$ global significance of peak search can correspond to approximately $4σ$ significance of the binary test for the same value of the observed test statistic. This reformulation provides a clearer statistical interpretation of the look-elsewhere effect and offers a more coherent framework for understanding significance claims in particle physics.

hep-ex↗

Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning

Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation. Tool augmentation offers a natural solution, while existing methods either plan tool calls from scratch without explicit dependency constraints or rely on fixed pipelines that are redundant and generalize poorly across spatial tasks. An effective spatial reasoning agent should instead accumulate reusable experience and adaptively compose it for new problems. To this end, we propose NeSy-Spatial, a neuro-symbolic framework for self-evolving spatial skills. NeSy-Spatial abstracts tool interactions and geometric operations into typed executable atomic instructions and composes them into two complementary skill types: Tool-Use Skills for organizing tool execution and Geometry Skills for structured geometric reasoning. During inference, NeSy-Spatial retrieves and executes relevant skills in a closed-loop process. During evolution, it analyzes buffered successful and failed trajectories to refine skill structures and prune unreliable or inactive entries. Experiments on three spatial reasoning benchmarks show that NeSy-Spatial consistently improves reasoning accuracy with more precise tool utilization.

cs.AI↗

NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing

Remote sensing underpins crucial applications such as disaster relief and ecological field surveys, where systems must understand complex scenes and constraints and make reliable decisions. Current remote-sensing benchmarks mainly focus on evaluating perception and reasoning capabilities of multimodal large language models (MLLMs). They fail to assess planning capability, stemming either from the difficulty of curating and validating planning tasks at scale or from evaluation protocols that are inaccurate and inadequate. To address these limitations, we introduce NeSy-Route, a large-scale neuro-symbolic benchmark for constrained route planning in remote sensing. Within this benchmark, we introduce an automated data-generation framework that integrates high-fidelity semantic masks with heuristic search to produce diverse route-planning tasks with provably optimal solutions. This allows NeSy-Route to comprehensively evaluate planning across 10,821 route-planning samples, nearly 10 times larger than the largest prior benchmark. Furthermore, a three-level hierarchical neuro-symbolic evaluation protocol is developed to enable accurate assessment and support fine-grained analysis on perception, reasoning, and planning simultaneously. Our comprehensive evaluation of various state-of-the-art MLLMs demonstrates that existing MLLMs show significant deficiencies in perception and planning capabilities. We hope NeSy-Route can support further research and development of more powerful MLLMs for remote sensing. The dataset and code are available at https://mingyang1010.github.io/NeSy-Route/.

cs.AI↗

Precision three-Dimensional Atmospheric Neutrino Flux Calculation Based on Honda Flux Model

We present a comprehensive three-dimensional atmospheric neutrino flux calculation based on the well-recognized simulation framework develeped by Honda and his collaborators, incorporating for the first time the muon propagation inside the Earth and its subsequent decay or nuclear capture. Other updates of essential input models include: the AMS02-based primary cosmic ray model, IGRF2020 geomagnetic field, and muon-recalibrated hadronic interaction model. The calculation covers seven detector sites across diverse geomagnetic environments, spanning 10~MeV to $10^4$~GeV. Significant site-dependent differences appear at $E_ν< 10$~GeV, with $ν_μ$ flux at IceCube approximately twice that at JUNO below 1~GeV. Compared to HKKMS15, deviations of 2\%--10\% are attributed to the updated input models. Below 100~MeV, we present precise flux results, revealing that muon propagation contributes a globally significant component to the low-energy neutrino flux at all sites, with an approximately site-independent absolute increment. The hadronic uncertainty is re-estimated across the energy range using the updated hadronic interaction model, with significant reduction of the systematic error compared to previous calculations. These results provide essential inputs for neutrino oscillation and rare-event search experiments including JUNO, Super-Kamiokande/Hyper-Kamiokande, DUNE, KM3NeT/ORCA, and IceCube, as well as direct dark matter detection experiments facing the neutrino fog.

hep-ph↗

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language. To address this gap, we introduce Pianist Transformer, with three key contributions: 1) introducing large-scale self-supervised learning into expressive piano performance rendering through a unified Musical Instrument Digital Interface (MIDI) representation, enabling pre-training on 10B tokens of unlabeled MIDI data; 2) an efficient asymmetric Transformer with note-level compression, substantially improving training efficiency, memory usage, and inference speed for long-context music modeling; 3) a state-of-the-art rendering model with an editable workflow, achieving strong objective and subjective results and enabling integration into real-world music production workflows. Overall, Pianist Transformer outlines a scalable path toward human-like performance synthesis in the music domain. Code, audio samples, and model checkpoints are available on our project page: https://yhj137.github.io/pianist-transformer-demo/.

cs.SD↗