Searcharxiv⌕ Search

arXiv subjects

Jin Li

Publications and source records attributed to Jin Li.

At least 19 recordsLinked to original sources
arXiv2026

LLM4Robot-Bench: How Far Can GPT-6 Astra Go in Robotic Manipulation? A Hierarchical, Paired Sim-Real Benchmark

We introduce LLM4Robot-Bench, a hierarchical, paired Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the 16 tasks have identical success counts across environments; the remaining six differ by one success out of three trials. Across both environments, recurring difficulties in spatial reasoning, contact selection, force regulation, and coordination often prevent local physical progress from accumulating into task completion. These findings characterize Astra's observed capability boundary across increasing interaction demands and, for this model, support matched simulation as a repeatable, scalable testbed for studying the sustained, coordinated physical interactions that limit reliable manipulation.

cs.RO↗
arXiv2026

A Unified AI Framework for Rapid and Accurate Waveform Generation of Compact Binary Coalescences

The astrophysical discovery potential of future gravitational wave detectors will hinge on accurate and rapid waveform generation. Third generation detectors are expected to observe many long duration compact binary coalescence signals that can probe binary formation and evolution as well as the nature of matter under extreme conditions. We develop a unified framework that combines physical modeling with deep learning. The framework uses an analytic residual spectral representation, shared learning, and decoders for each binary type. It generates waveforms for binary black holes, binary neutron stars, and neutron star black hole binaries, providing a single unified generator for all compact binary coalescences. The generated waveforms include the physical effects described by each reference model, such as spin precession, higher order modes, matter effects, and postmerger radiation for binary neutron stars. The waveforms span hundreds to thousands of cycles, with mean mismatches ranging from $5.89\times10^{-4}$ to $5.34\times10^{-2}$ relative to the reference waveforms. Batch generation achieves a maximum speedup of about 1800 over reference waveform generation.

gr-qc↗
arXiv2026

Full-Stokes response to a stochastic gravitational-wave background in pulsar timing arrays: Fully analytic overlap reduction functions at finite distance and coherence of close pulsar pairs

We derive fully analytic overlap reduction functions for the full-Stokes response of a pulsar timing array to an anisotropic tensor gravitational-wave background in general relativity. The response retains both pulsar distances and their complete propagation phases. At each fixed finite sky multipole, the intensity and circular polarization responses reduce to finite combinations involving exponential integrals and logarithms, while the electric and magnetic linear polarization responses require only elementary functions. We evaluate all components through $\ell=8$. Symmetry separates exact nulls from additional Earth-term nulls that propagation can lift. Even an unpolarized background can produce an imaginary cross-spectrum. For a pair with three-dimensional separation $d$, the pulsar terms can remain coherent when $2πfd/c\lesssim1$, even if both pulsars are many wavelengths from Earth. A uniform approximation retaining all four Earth and pulsar terms connects this regime to the short-wavelength limit, and a rotationally invariant relation fixes the leading transverse magnetic response. Common-distance errors cancel from the aligned pair phase, while relative-depth errors directly affect coherence. Under Gaussian differential averaging, fixed low-multipole norms and the squared norm summed over all multipoles decay at different rates as the response shifts to higher multipoles. Published pulsar configurations illustrate the roles of distance accuracy, bandwidth, and timing fits. At fixed pointwise intensity, a polarization covariance bound and a relative-depth noise budget quantify when differencing suppresses the background. Independent sky integration and matched-accuracy benchmarks test the analytic expressions over the parameter ranges studied.

gr-qc↗
arXiv2026

Characterizations and MacWilliams-Like Identities of Weakly Regular Bent Partitions

Bent partitions play a significant role in the theory of bent functions. In this paper, we study weakly regular bent partitions, that is, all generated bent functions are weakly regular (called in class $\mathcal{WRBP}$). Let $Γ=\{A_{i}, i \in V_{m}\}$ be a bent partition of $V_{n}$ in class $\mathcal{WRBP}$, where $V_{n}$ denotes an $n$-dimensional vector space over the prime field $\mathbb{F}_{p}$, $n$ is even, $m \leq \frac{n}{2}$, and $m \geq 2$ if $p=2$. We first characterize bent partition $Γ$ in terms of the duals of component functions of vectorial bent functions. In particular, we prove that if $p \neq 3$, then all bent functions generated by $Γ$ are regular. Building on the above result, we give characterizations of bent partition $Γ$ in terms of two classes of linear codes. When $n \geq 4$ and $m=\frac{n}{2}$, except for the case where $(p, n)=(2, 4)$ and $|A_{i_{0}}|=1$ for some $i_{0}$, we show that $Γ$ is obtained from a spread (after a shift). Particularly, any normal bent partition of $V_{n}$ of depth $p^{\frac{n}{2}}$ in class $\mathcal{WRBP}$ must be obtained from a spread (after a shift), where $n \geq 4$. We establish the Macwilliams-like identities for bent partitions in class $\mathcal{WRBP}$. Furthermore, if $p$ is odd, we present some nonexistence results on bent partitions in class $\mathcal{WRBP}$.

cs.IT↗
arXiv2026

Energy-flux noise induced by imperfections of the Gaussian beam in the Li-Baker HFGW detector

This paper investigates the energy-flux noise induced by imperfections of the Gaussian beam (GB) in the Li-Baker high-frequency gravitational wave (HFGW) detector. Modeling these imperfections with higher-order Laguerre-Gaussian (LG) beams, we analytically derive the resulting noise-to-signal ratio for both co- and cross-polarized $\mathrm{LG}_{nl}$ modes. It is found that higher-order co-polarized LG beams generate no tangential energy-flux noise at the optimal detection plane ($ϕ=π/2$ or $3π/2$), whereas higher-order cross-polarized LG beams introduce non-negligible noise. Specifically, for an individual higher-order cross-polarized $\mathrm{LG}_{nl}$ mode under our representative parameters, maintaining the noise-to-signal ratio below unity typically requires the power fraction to satisfy $σ_{nl}<10^{-46}$, with the $\mathrm{LG}_{01}$ mode imposing the most stringent constraint of $σ_{01}<6.0\times10^{-49}$. Monte Carlo simulations suggest that the total power fraction $σ_{\mathrm{total}}$ of multiple higher-order cross-polarized $\mathrm{LG}_{nl}$ modes needs to remain below $10^{-49}$. Consequently, we propose employing a polarization filter to retain only the co-polarized component of the GB adopted in the practical experiment, thereby suppressing the noise while preserving signal integrity. These results provide theoretical guidance for noise control in the Li-Baker HFGW detector.

gr-qc↗
arXiv2026

UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation

Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of work address this from complementary angles: Representation Alignment (REPA) accelerates DiT training by aligning intermediate features with a pretrained external representation model (e.g., DINOv2), while Representation Auto-Encoders (RAE) replace the pixel-space VAE with a compact representation-space tokenizer learned from self-supervised features. However, these approaches are developed and applied in isolation: REPA still relies on a pixel-space VAE for latent diffusion, and RAE does not exploit the alignment signal that accelerates the diffusion backbone. We present \textbf{UniRA}, a unified framework that couples representation alignment and representation auto-encoding into a single objective. UniRA learns a representation-space tokenizer whose output serves simultaneously as the diffusion target and the alignment anchor, so the tokenizer, the diffusion backbone, and the external representation model are co-optimized. We give a theoretical result showing that this joint optimization preserves the representation quality of the external model while accelerating diffusion convergence, and we derive a principled weighting that balances the reconstruction, alignment, and generation objectives. On ImageNet class-conditional generation at 256*256 and 512*512, UniRA matches or surpasses state-of-the-art DiTs (SD3, REPA, RAE) in FID while reducing training steps by up to 5*. We further show that the unified representation space supports improved zero-shot classification and linear probing, confirming that generation and understanding benefit from a shared, aligned latent space.

cs.CV↗
arXiv2026

Anisotropic overlap reduction functions for arbitrary equal-arm TDI channels: A fully analytic framework and efficient evaluation

We establish a unified analytic framework for anisotropic overlap reduction functions (ORFs) of arbitrary finite-delay time-delay interferometry (TDI) channels in a static, reciprocal, equal-arm equilateral constellation. The construction combines the polynomial constraints for laser-noise cancellation, constellation symmetries, and directional-projection integration. A free basis of the admissible channel module separates channel generation from angular integration; two families of elementary angular kernels then generate all channel-pair intensity ORFs. The channel algebra is independent of gravitational-wave polarization, and the intensity-kernel reduction applies to tensor, vector, breathing, and longitudinal sectors. Tensor multipoles illustrate the framework here. Complete propagation effects are retained at arbitrary fixed finite angular order, with explicit examples through $\ell=5$. Prepared frequency batches, shared multiprecision expressions, and local expansions at removable delay points provide stable evaluation. In the prepared-batch benchmark, the analytic implementation is approximately 50 to 5000 times faster than optimized sky quadrature at matched error tolerances. Independent multiprecision sky integrations also validate prescribed mixed error targets down to $10^{-100}$ in the tested cases. The resulting kernels and generation rules supply reusable inputs for anisotropic multichannel background models.

gr-qc↗
arXiv2026

In situ enhanced detectability of axions' responses in a microwave cavity

Microwave cavities in strong magnetic fields are among the most sensitive detectors for axion dark matter detection. Its sensitivity, however, is fundamentally limited by the second order nature of axion photon energy conversion, which yields an extremely weak signal. Here we propose a feasible approach to break this limitation, by pre-exciting the target cavity mode to generate a first order power response signal in situ. The resulting signal amplitude scales linearly with the axion-photon coupling parameter, which is in sharp contrast to the quadratic scaling of conventional schemes, and is detectable via standard quadrature balanced homodyne detection system, even though its phase remains stochastic. Numerical simulations demonstrate that this pre-excited seed field can effectively suppress thermal noise, and thus the detection sensitivity of the system can approach the lower quantum noise limit. Consequently, the sensitivities predicted by the KSVZ and DFSZ models could be surpassed. This proposal might offer a pathway to a major leap in axion dark matter searches, as it is within reach of current technology.

hep-ph↗
arXiv2026

Automating the Design of Embodied Agent Architectures

Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been systematically evaluated on perceptual embodied agents. We study this transfer. To make embodied architectures searchable, we introduce AgentCanvas on the executor side, representing embodied agents as editable typed graphs with simulator execution and episode-level logs. On the optimizer side, we lift AAS from LLM-call loops to tool-using coding-agent sessions, adapting ADAS and AFlow and introducing Knowledge Distill Loop (KDLoop). Across four embodied executors (MapGPT, SmartWay, ExploreEQA, and VoxPoser), search discovers improvements that persist on episodes never queried during search. KDLoop and AFlow independently discover elevation-tolerant observation processing. KDLoop's implementation also improves success rates over the baseline when transferred to real robots. These improvements are not uniform: some gains remain uncertain or reverse on held-out episodes, and an apparent gain exploits evaluator-side information. The experiments further show how rollout noise, local edit basins, and incomplete use of episode-level evidence constrain search. Together, these results establish the potential of automated architecture search for embodied agents and characterize the challenges of applying it in simulated and real-world environments. Code is available at https://github.com/jianzhou0420/AgentCanvas.

cs.RO↗
arXiv2026

HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation

Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one independent hospital is involved, multi-center MR with hospitals of different scales has become increasingly demanding in practice. In multi center settings, abundant data from large medical centers can improve recommendation performance for low-resource centers. Despite a few preliminary attempts on this task, two critical gaps remain. Gap 1: Existing multi-center methods fail to disentangle transferable cross-hospital clinical experience from hospital-specific prescribing patterns, limiting clinical feasibility and physician acceptance. Gap 2: They commonly overlook multi label safety constraints of MR, including drug-drug interaction risks and local formulary feasibility, which are essential for safe real-world deployment. To address these gaps, we propose HEM-Med, a novel hierarchical agentic memory framework for multi-center MR. To address Gap 1, we design a disentangled hierarchical memory module that builds patient-level medication context attribution records and disentangles them into cross hospital experience memory and hospital-specific residual memory. To address Gap 2, we introduce a safety-aware medication set generation module, which integrates dual-level experience retrieval with safety-aware set decoding to produce clinically relevant, safer, and locally adaptive medication recommendations. Experiments on a real-world multi-center eICU dataset show that HEM-Med outperforms representative transfer learning, LLM-based, and MR baselines in terms of both recommendation accuracy and safety.

cs.AI↗
arXiv2026

Praxist: From Experimental Artifacts to Solution Lineages

Autonomous R&D agents now write, run, and improve executable artifacts under automated evaluation-but largely as laboratory instruments: shown on curated benchmarks, with gains that are hard to trace to a cause and costs well above what sustained engineering practice absorbs. The limitation is structural. Most systems treat each attempt as nearly self-contained, so logs, memories, and search trees record what happened without establishing which design element produced an improvement, whether its evidence survived validation, or how it recombines with others. Long campaigns therefore keep re-learning the same lessons. We introduce Praxist, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas. Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated mechanisms, unresolved claims, and useful constraints, and leaves results attached to an inspectable lineage. On the standardized 75-task MLE-bench suite, the finalized official-grader results give Praxist 60 medals (80.0%), 49 of them gold, against 55 medals (73.3%) and 34 gold for a Claude Code baseline on Claude Opus 4.8-at a recorded model spend of $3054 versus $38370, roughly a twelfth of the cost. Five case studies-quantitative trading, LiDAR-inertial-visual SLAM, tokamak magnetic control, rocket landing, and job-shop rescheduling-carry the same process into open-ended engineering problems, improving on each task-native baseline in headline accuracy, survival, or resource cost, with the discovery path on record. Stronger artifacts at an order of magnitude less spend, each backed by an auditable lineage, are, to our knowledge, first brought together here: the operating profile production research requires, not the one a benchmark demonstration establishes.

cs.MA↗
arXiv2026

OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536\times1536$). The dataset combines Gemini-powered dense captioning with stratified sampling across 20 visual clusters obtained by DINOv3 K-Means. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Under the specified evaluation rubric, our representation metric shows strong agreement with human model rankings (Kendall's $τ$ of 0.833 vs. 0.611 for SSIM). Code and dataset are available at https://github.com/RenxingIntelligence/OpenVTON-Bench.

cs.CV↗
arXiv2026

RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation

Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decision-making and personalized safety are of paramount importance. However, existing approaches predominantly operate as ``black boxes'', offering limited interpretability and hindering clinician trust. Furthermore, they typically rely on fixed, patient-agnostic safety constraints, neglecting the heterogeneity of risk tolerance across individuals, which poses significant risks to vulnerable populations. To address these gaps, we propose \textbf{RES-MR}, a novel Risk-aware Reasoning framework for Explainable and Safe Medication Recommendation using LLMs. RES-MR follows a two-stage training paradigm: (1) an explainable clinical reasoning distillation stage to elicit diagnostic capabilities by fine-tuning on synthesized reasoning trajectories, grounded in patient-specific knowledge from graph retrieval; and (2) a risk-aware policy optimization stage to dynamically balance therapeutic efficacy with personalized safety. This stage employs disentangled drug factors to construct patient-specific reference prototypes that capture desired therapeutic drug features and risk features to avoid. These prototypes enable risk boundary calibration and guide the model toward safe recommendations via reward shaping and clipping. Extensive experiments on benchmark datasets demonstrate that RES-MR significantly outperforms state-of-the-art baselines in terms of accuracy, safety, and explainability. Our code and data are available at: https://github.com/wangcong2001/RES-MR.

cs.LG↗
arXiv2026

Hierarchical Reasoning Model

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose the Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency. HRM executes sequential reasoning tasks in a single forward pass without explicit supervision of the intermediate process, through two interdependent recurrent modules: a high-level module responsible for slow, abstract planning, and a low-level module handling rapid, detailed computations. With only 27 million parameters, HRM achieves exceptional performance on complex reasoning tasks using only 1000 training samples. The model operates without pre-training or CoT data, yet achieves nearly perfect performance on challenging tasks including complex Sudoku puzzles and optimal path finding in large mazes. Furthermore, HRM outperforms much larger models with significantly longer context windows on the Abstraction and Reasoning Corpus (ARC), a key benchmark for measuring artificial general intelligence capabilities. These results underscore HRM's potential as a transformative advancement toward universal computation and general-purpose reasoning systems.

cs.AI↗
arXiv2026

Gaussian Relational Graph Transformer

Relational graph learning enables predictive modeling over relational databases by directly capturing dependencies across interconnected tables. While relational graph Transformers extend the receptive field beyond local message passing, a larger receptive field does not necessarily provide more useful information: sampling must preserve relational structure without introducing excessive semantically irrelevant nodes, while attention must account for the temporal relevance of the retained information. We propose GelGT, a Gaussian relational graph transformer that explicitly addresses these challenges. GelGT introduces a structure-semantic collaborative sampling strategy to preserve structural connectivity while filtering irrelevant semantic information, and incorporates a Gaussian graph attention mechanism with a learnable Gaussian bias on the sampled subgraphs to dynamically encode temporal dependencies. We provide theoretical analysis characterizing the structural preservation, semantic refinement, and temporal discrimination of these mechanisms. Experiments on \textbf{7} real-world relational datasets covering \textbf{21} prediction tasks show that GelGT consistently outperforms existing relational graph learning methods, with improvements of up to \textbf{13.8\%}.

cs.LG↗
arXiv2026

When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation

Rehearsal-free continual learning with parameter-efficient adapters can be cast as a sequence of task-vector write-in operations: for each new task, a low-rank adapter is learned and merged into a running model. We propose Proximity Regularized Merging (PRM), a minimal modification to sequential LoRA merging that adds a proximal penalty during task-vector training without changing the subsequent write-in rule. PRM acts as a robust task-vector regularizer: in the reported Base->+Prox diagnostics, it improves AAA across multiple write-in rules, backbones, and class-incremental settings, while its fixed-coefficient variant remains competitive with strong coefficient-based baselines. Mechanistically, matched-prefix norm controls and proximal-strength sweeps show that proximal training shrinks the task-vector radius, lowers Fisher-weighted interference, broadens the coefficient plateau, and exposes a stability-plasticity trade-off. Together, these results suggest that the effectiveness of sequential LoRA merging depends not only on how much of a task vector is written in, but also on whether the task vector itself has been trained to be mergeable.

cs.LG↗
arXiv2026

Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers

On-policy reasoning models can learn from task rewards or teacher signals, but these sources differ in form and can favor conflicting updates, leaving unclear which should guide a given reasoning action. We introduce \textbf{Expected Reasoning-Step Return (ERSR)}, which treats semantic reasoning steps as macro-actions and uses Monte Carlo student-policy rollouts to estimate the expected final task reward of student-generated and teacher-proposed actions in a common return space for step-level comparison. ERSR analysis reveals an outcome-dependent asymmetry: student actions are more beneficial than teacher replacements on successful trajectories, whereas teacher replacements become more beneficial on failed trajectories. We further show that student answer-probe gains track student-step ERSR utility and distinguish beneficial from harmful reasoning steps. Based on these findings, we propose \textbf{Return-Referenced On-Policy Learning (R$^2$OPL)}, which reinforces student reasoning on successful trajectories and distills teacher signals on failed ones, while using group success rate for difficulty scaling and student-probe gains for step-level modulation. Experiments across reasoning benchmarks and teacher--student configurations show that R$^2$OPL consistently outperforms strong baselines. ERSR training dynamics further show that R$^2$OPL jointly exploits substantial utility from both reward- and teacher-side signals, whereas existing hybrids often leave substantial residual utility in one branch.

cs.AI↗
arXiv2026

When Less Is More: Managing AI Adoption with Adaptive Incentive Design

We study gaming and adaptive incentive design in AI adoption. A large medical-device company required roughly 5,000 employees to submit at least 200 queries per month to an internal AI assistant. First-time use increased significantly after the mandate, but usage patterns suggested gaming: query counts bunched at the threshold, and 31 percent of queries were repeated or off-task. The firm subsequently revised incentive design and lowered the target to 100. Using staggered implementation across branches, we estimate that the adjustment reduced query volume by 30 percent, with repeated or off-task queries accounting for about 90 percent of the decline. The estimated change in non-repeated, work-related queries was small and statistically insignificant. Among sales employees, monthly sales increased by 7 percent. The findings identify incentive adaptation as a consequential margin of technology adoption: recalibrating usage requirements can reduce gaming and improve employee performance.

econ.GN↗