Search arXiv⌕ Search

arXiv subjects

Jin Li

Publications and source records attributed to Jin Li.

At least 19 recordsLinked to original sources
arXiv2026

How High Can GPT-6 Astra Climb in Contact-Rich Manipulation? PhysLadder: A Hierarchical, Matched Sim-Real Benchmark for Physical Interaction

We introduce PhysLadder, a hierarchical 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

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↗
arXiv2026

Shrinking-Tube Concentration for Adaptive Markovian Stochastic Approximation

Adaptive algorithms increasingly make decisions while reshaping the dynamics that generate their future data. We establish a shrinking-tube concentration bound for projected stochastic approximation driven by an adaptive Markov chain. The bound guarantees, with high probability, that every iterate after a chosen time remains within a tolerance around the target that tightens over time. The probability of any exit after the chosen time admits a polynomially decaying upper bound, and a matching lower bound shows that its polynomial exponent cannot be improved in general under finite second moments. The result therefore identifies a sharp tradeoff between how quickly the tolerance shrinks and how rapidly the probability of any future exit decreases. We also extend the analysis to recursions with additional martingale-difference noise and predictable bias, showing how growth in the martingale-difference noise scale slows the decay of the exit-probability bound while predictable bias restricts the admissible tube shrinkage. The proof combines backward kernel replacement, a finite-time mean-squared-error bound, and a blockwise maximal first-exit argument. We apply the theory to inventory learning with stockout-dependent demand and fixed stockout costs, and quantify how numerical gradient accuracy affects the all-future reliability of the resulting policies.

math.OC↗
arXiv2026

Tests of general relativity using analytic derivatives of parametrized post-Einsteinian gravitational waveforms within the Fisher-matrix framework

Testing gravity beyond general relativity (GR) is essential for probing fundamental physics in the strong-field and highly dynamical regime accessed by gravitational-wave (GW) observations. In this work, we derive analytic expressions for waveform derivatives in the Fisher-matrix formalism within the parametrized post-Einsteinian framework, using the frequency-domain inspiral waveform. These analytic derivatives enable stable and efficient Fisher-matrix calculations without relying on finite-difference schemes. We apply this method to a wide range of detector configurations, including space-based, ground-based, and multiband observations, and combine it with different binary black hole population models. Our results reveal clear and systematic trends in the constraints on non-GR effects as functions of post-Newtonian order, detector type, and source population. They also demonstrate the complementarity between space- and ground-based detectors, particularly for effects that accumulate during the low-frequency inspiral. The analytic approach substantially reduces computational cost and avoids numerical systematics associated with step-size choices, making it well suited for large-scale parameter studies. These results provide robust forecasts for the capability of future GW observations to constrain a broad class of non-GR effects and environmental influences, highlighting the scientific potential of upcoming detector networks for precision tests of gravity.

gr-qc↗
arXiv2026

From Research Frontier to Laboratory Bench: Design of a Four-Tier Experimental Teaching System for Multimodal Medical Image Intelligent Diagnosis

Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long-tailed, and distributionally shifting realities of clinical AI. This design paper presents an advanced experimental teaching system that translates an ongoing multimodal deep learning research project on endometrial carcinoma into a structured undergraduate lab sequence. We identify three educational gaps (modality, authenticity, and deployment) and derive four pedagogical principles from constructive alignment, experiential learning, the research teaching nexus, and the CDIO framework. The curriculum comprises four progressive tiers plus an engineering layer, with 32 laboratory units over 64 contact hours, delivered via a custom virtual clinical workstation using de-identified multi-institutional data. Each tier maps to a specific technical bottleneck, prerequisite coursework, and criterion-referenced deliverables. Data governance, safety, and assessment protocols are specified. Learning outcome data will be collected across two implementation cycles.

cs.AI↗
arXiv2026

Calibrating Teacher--Student Discrepancy for On-Policy Distillation

On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does not purely reflect the capability gap between the teacher and the student: it also contains deviations arising from the teacher itself, which are consequently mixed into the observed teacher--student discrepancy and indiscriminately learned by standard OPD during training. This issue is further exacerbated by privileged OPD, where privileged information induces larger teacher-side likelihood shifts, thereby encouraging the student to learn more of the teacher's own deviation. We introduce \textbf{Calibrated On-Policy Distillation (Cal-OPD)}, which estimates the teacher's self-deviation region through positive and negative privileged interventions and calibrates the original teacher--student discrepancy by retaining only the component that lies beyond this region. Experiments on mathematical reasoning benchmarks show that, while retaining only about 52--65\% of the original teacher--student discrepancy as the optimization signal, Cal-OPD consistently outperforms standard OPD and its variants across model scales.

cs.AI↗
arXiv2026

A Matrix-free Augmented High Order Compact Solver for Variable-Coefficient Biharmonic Problems

We propose an augmented high-order compact finite difference method for biharmonic equations with clamped boundary conditions and variable coefficients. Standard mixed-type formulations introduce an auxiliary variable, but its boundary values are unavailable, leaving the resulting discrete systems globally coupled and difficult to solve at large scales. Our key contribution is the development of a new augmented formulation that treats these unavailable boundary values as additional unknowns, reduces the global coupling to a lower-dimensional Schur complement system, and yields decoupled second-order subproblems. The Schur complement is solved by matrix-free GMRES, while the subproblems are handled by FFT-based fast solvers. The method achieves fourth-order accuracy using compact stencils, and has $O(n\log n)$ computational complexity, enabling the solution of the biharmonic equation with $1024^3$ degrees of freedom within several minutes. To the best of our knowledge, this level of computational efficiency has not previously been achieved in either the literature or practice. Using energy estimates and Fourier analysis, we derive a new $L^2$-estimate for Poisson equations with inexact Dirichlet boundary and then prove the convergence of the proposed scheme. We provide ample numerical experiments to confirm the accuracy, efficiency, and further apply the fast and accurate solver to triharmonic equations, high-wavenumber problems, Stokes flow, and plate bending problems.

math.NA↗
arXiv2026

Cosmological Evolution of the Randall-Sundrum II Model with Running Vacuum: A Special Class of Solutions

In this work, we construct a novel cosmological framework by integrating the running vacuum model into the Randall-Sundrum II braneworld scenario. We derive a special class of analytical solutions in the model. Our investigation focuses on the complete evolutionary trajectory of the universe, with particular emphasis on the realization of primordial inflation and the evolution of cosmic entropy. We evaluate the model's viability across three scenarios: dust-dominated, radiation-dominated, and general perfect fluid-dominated universes. Our findings show that while the hybrid model is in principle capable of supporting inflation, producing enough e-fold number demands either severe fine-tuning of the parameter or unreasonably large (and thus physically unnatural) value of the parameter.

gr-qc↗