arXiv subjects

Yixuan Li

Publications and source records attributed to Yixuan Li.

At least 19 recordsLinked to original sources

arXiv2026

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, and understand the settings behind reported scores. We present Benchmark Radar, a living database and search engine for retrieval and discovery of AI benchmarks, covering LLM evaluation, agentic and tool-use benchmarks, coding, reasoning, safety, and domain-specific evaluations. The system combines daily discovery of benchmark papers, repositories, datasets, and releases with a searchable benchmark catalog, mentions in model cards and technical reports, and score histories. It retains source identities and citations so readers can inspect candidate benchmarks and their evaluation evidence. Daily discovery draws on 37 sources: 13 direct connectors and 24 first-party research and engineering feeds. The catalog contains 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 records. We describe collection and retrieval, audit the full catalog, and examine benchmark saturation, adoption trends, and the limits of score comparisons. A worked example walks through a complete prior-art search, showing how to query the catalog and inspect benchmark evidence when designing a new evaluation. We release the web dashboard with a benchmark leaderboard, a Pareto frontier view of score against measured use, saturation and trend views, daily feeds, downloadable evidence, a command-line interface (CLI) for offline queries, and reproducible analysis.

cs.AI↗

arXiv2026

Bodyseismography (BSG): Theoretical Foundation and Numerical Modeling

Bodyseismography (BSG) records cardiovascular vibrations transmitted through the body and a supporting bed, enabling contactless assessment of cardiac mechanics. Relating these vibrations to hemodynamic features requires separating cardiac excitation from the effects of body and bed transmission. We develop a source-transmission-measurement framework that couples myocardial contraction and vascular recoil to directional BSG observations. The theory connects stroke volume, cardiac output, and blood pressure to observation and target Jacobians, establishes a local first-order target-observability criterion, and characterizes how additional sensing axes reduce ambiguities under specified source and transmission uncertainties. Numerical modeling combines four-chamber cardiac mechanics, cardiac-to-body excitation, and calibrated body-bed operators. Across 27 participants, a multilayer finite-element model with calibrated frequency correction achieves median Pearson correlation coefficients of 0.865 for the vertical channel and 0.682 for the planar-sum channel in matched-window waveform reconstruction. Controlled stroke-volume perturbations show that transmission reshapes feature sensitivity, including a reversal of the vertical feature association in 8 of 27 participant-specific transfer models. These analytical and numerical studies explain how cardiovascular sources and mechanical propagation jointly shape triaxial BSG and provide a physical basis for relating directional vibration features to hemodynamic changes.

eess.SP↗

arXiv2026

Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data

Learning generalizable humanoid loco-manipulation remains bottlenecked by costly real-world demonstrations. Simulation provides a scalable alternative, but requires visually faithful, physics-ready scenes and executable whole-body motions. We present Zero-HLM, a real-to-sim-to-real framework that transforms smartphone captures and simulated source demonstrations into scalable training data for humanoid loco-manipulation. Gaussian-guided agentic real-to-sim reconstruction aligns visual and physical scenes; motion-environment co-adaptation uses rollout feedback to correct whole-body references and interaction geometry. We generate 4,800 physically validated demonstrations for zero-shot transfer across three Unitree G1 tasks. Simulation-trained GR00T N1.7 achieves 66.7% mean full-task success, versus 46.7% with real-data training. On generalized configurations, expanded simulation training raises pooled success from 23% for base-trained real-data policies to 69%, without additional real demonstrations. Project page: https://young-bit.github.io/zero-hlm/

cs.RO↗

arXiv2026

Of Chains and Gains: What Reinforcement Learning changes on Reasoning-based Image Quality Assessment

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the performance of large Vision-Language Models (VLMs) on image quality assessment (IQA). Existing approaches often attribute these gains to improved reasoning before scoring, supported by increasingly plausible Chain-of-Thought (CoT). However, whether these gains exceed sampling effects and how they depend on explicit reasoning remain unclear. We rigorously investigate these questions through sampling-aware evaluation, controlled reasoning interventions, and shortcut experiments. We find that RL-trained models outperform base models under large-budget $\operatorname{max}_g@k$ evaluation, while improvements beyond averaging are concentrated in-distribution. RLVR produces chains that raise base-model performance when transplanted and improves scoring with the chain held fixed. Yet scoring becomes less dependent on the chain during inference, more clearly at 7B than at 32B. Steering the probed quality direction in thinking tokens also has little effect on scoring. Finally, RL can improve scoring accuracy by exploiting textual cues correlated with mean opinion scores (MOSs), which could inflate benchmark performance. Together, these findings show that RLVR raises quality scoring and produces more useful chains, but that better scoring does not imply a stronger reliance on explicit reasoning, while score-based rewards can also encourage reliance on quality-irrelevant shortcuts. We hope this preliminary study can enlighten more and more concrete reasoning schemes in IQA.

cs.CV↗

arXiv2026

HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration

Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches provide execution flexibility but do not explicitly model subtask hierarchies or dependencies, while predefined workflows impose this structure but fix the decomposition before execution begins. Therefore, we introduce HTN-Orchestrate, a two-layer framework that separates these responsibilities through a hierarchical task network (HTN). The Planner maintains subtask hierarchies and dependencies, deferring decomposition until prerequisite results become available, while local Orchestrators schedule workers to execute each leaf subtask. Results propagate upward under \textbf{AND} semantics, and accumulated findings inform a rebuilt task network when the current decomposition cannot resolve the task. On five benchmarks spanning web research, scientific reasoning, and research workflows, HTN-Orchestrate outperforms ReAct, Agent Team, and DeepSeek Harness using the same base model, achieving 89.73% accuracy on BrowseComp and 73.44% on SUPERChem, exceeding Agent Team by 2.45 and 4.69 percentage points, respectively.

cs.AI↗

arXiv2026

Beyond Source Prompts: Towards Visually Grounded AI-Generated Video Quality Assessment

Recent advances in generative artificial intelligence have accelerated video generation technologies. However, AI-generated videos (AIGVs) remain susceptible to various distortions, highlighting the need for dedicated video quality assessment methods. Content semantics play an important role in AIGV quality assessment, with source prompts typically used as textual references. However, these prompts may not accurately reflect the generated video content, resulting in a discrepancy between the intended textual description and the generated result. To address this limitation, this paper proposes VGCap, an AIGV quality assessment framework guided by visually grounded captions that align better with generated content. Specifically, we introduce two forms of captions: a global caption obtained by minimally revising the source prompt based on multi-frame visual evidence, and prompt-independent segment captions that describe localized temporal content. Together, these captions provide complementary textual evidence for assessing spatial quality, temporal quality, and text-video alignment. Experimental results on the LGVQ and FETV datasets show that VGCap outperforms representative baselines across all three dimensions. Further ablation studies on caption sources and temporal components confirm the effectiveness of visually grounded captions for each quality dimension, while highlighting the benefits of segment-level features for temporal quality prediction. The source of VGCap will be available at https://github.com/lolo123-123/VGCap.

cs.CV↗

arXiv2026

SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation

Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts. This limitation is especially pronounced for rare and fine-grained clinical codes in long-tailed vocabularies, where hierarchy-agnostic LM representations become less informative as concept frequency decreases. We introduce Semantic Medical Identifier (SMI), a training-free framework for constructing ontology-grounded Semantic IDs and hierarchy-aware medical concept representations. For each diagnosis, procedure, or medication concept, SMI defines its Semantic ID as the coarse-to-fine path through an expert-defined medical ontology. SMI then aggregates frozen biomedical LM embeddings across the corresponding ontology levels to form hierarchy-aware medical concept representations that preserve coarse-to-fine clinical semantics. The base SMI uses uniform aggregation across ontology levels, while a level-weighted variant selects global level weights on validation data. Our theoretical analysis shows that SMI yields more informative medical concept representations than hierarchy-agnostic LM embeddings, particularly for rare and fine-grained clinical concepts. Experiments show that SMI captures meaningful hierarchical structure and improves clinical relation prediction. On MIMIC-IV, SMI improves mortality prediction, readmission prediction, drug recommendation, and rare drug prediction. On eICU, SMI yields more robust patient representations under cross-hospital distribution shift.

cs.CL↗

arXiv2026

Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction

Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability. Graph neural networks (GNNs) complement LMs by incorporating inter-patient relationships and enabling reference-patient attribution, yet they rely on high-quality patient representations. We propose Patients-like-me (PLM), a unified LM--GNN framework that integrates local patient semantics with global cohort structure. To train PLM efficiently, we introduce a Variational Expectation-Maximization algorithm that alternates LM and GNN updates under a supervised variational objective. Extensive experiments on MIMIC-III and MIMIC-IV show that PLM consistently outperforms state-of-the-art methods, with improvements generalizing across encoder-only and decoder-only LM backbones. These gains are achieved with only modest additional computational overhead. PLM also provides reference-patient explanations by retrieving influential similar patients, while edge-masking experiments confirm that the highest-ranked references have the greatest impact on model predictions.

cs.CL↗

arXiv2026

The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks

Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization, pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-inference computation cost and inter-action latency. However, unlike traditional static ML tasks, embodied tasks involve repeated interaction with the environment, and task-level performance is determined not only by inference cost, but also by closed-loop effects unique to embodied execution, which remain insufficiently characterized in current efficient-inference studies. In this work, we propose TISED (\underline{T}ask-level \underline{I}nference \underline{S}peedup \underline{E}ffect \underline{D}ecomposition), an analytical framework that unifies diverse lossy lightweighting inference optimization techniques and decomposes their effects on static and dynamic tasks; using it, we uncover several paradoxical effects: (1) on \textit{static tasks}, optimization can sometimes lengthen end-to-end per-task completion time even as per-chunk time drops; (2) on \textit{dynamic tasks}, moderate lossy lightweighting optimization can raise task success rate even above the baseline; and (3) the monotonicity and sweet-spot location of both effects can shift with hardware configuration. Together, our findings provide a new perspective on adapting inference optimization techniques to embodied tasks. Source code: https://github.com/thu-ee-acts-lab/robotics-the-speedup-paradox.

cs.RO↗

arXiv2026

AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation

Speech-conditioned generation maps speech signals to target audio outputs. Prior end-to-end speech-conditioned generative models achieve high fidelity in clean acoustic conditions, but their performance degrades substantially under environmental noise. While prior noise-robust approaches have achieved significant success in feature-level purification, maintaining consistent generation under clean and noisy conditioning remains a key challenge. To address this, we propose AlignAudio, a noise-robust generative framework based on dual alignment: (i) aligning the representations of clean and noisy speech to preserve semantic cues, and (ii) enforcing generation-level consistency within a flow matching paradigm to improve conditioning fidelity. Experiments on speech-to-audio (STA) and voice conversion (VC) tasks demonstrate that AlignAudio maintains performance comparable to baselines on clean speech while significantly outperforming them across various noisy conditions. Furthermore, the proposed dual-alignment strategy is applicable to both single- and multi-stream speech conditioning and can be integrated into different flow matching-based generation frameworks and post-training settings. Audio demonstrations and qualitative comparisons: \href{https://alignaudio.github.io/AlignAudio}{\textcolor{cyan}{\textit{https://alignaudio.github.io/AlignAudio}}}.

cs.SD↗

arXiv2026

C2Flight: A Closed-Loop Co-Simulation Framework for Early-Stage Evaluation of Heterogeneous UAV Computing Systems

Early-stage design of heterogeneous UAV computing systems requires evaluating how algorithm, hardware, communication, and system topology affect closed-loop flight before the complete system is available. However, design choices interact through the robotic feedback loop, making task performance difficult to predict from isolated component metrics, while existing execution-driven approaches postpone system-level design feedback until the computing system is integrated. This work presents C2Flight, a closed-loop co-simulation framework that represents target systems as parameterized dataflow graphs and integrates models of hardware under design with independently accessible physical hardware through a unified node interface. Its graph runtime captures the combined effects of buffering, activation, resource sharing, communication, and local timing on closed-loop flight behavior. Validation against onboard and wireless offboard physical computing pipelines confirms its timing fidelity and closed-loop prediction accuracy. Two case studies demonstrate early-stage exploration of deployment and accelerator bit-width choices. These results show that C2Flight exposes system-level design trade-offs before full-system integration, enabling rapid early-stage design refinement.

cs.RO↗

arXiv2026

SWEAR: Section-Wise Efficient Audio Reasoning via Self-Rated Difficulty

Recent work on large audio-language models (LALMs) explores adaptive reasoning to balance accuracy and efficiency. However, existing approaches often rely on coarse-grained difficulty estimation, overlooking the diverse factors that determine reasoning effort. We address this limitation by deriving five-dimensional difficulty scores and compressed reasoning traces from complementary offline assessments. Based on this characterization, we propose SWEAR, a difficulty-aware reasoning framework that learns difficulty signals during supervised fine-tuning and uses reinforcement learning to adapt reasoning allocation across reasoning stages. Experiments on MMAU-test-mini and MMAR show that SWEAR improves accuracy while substantially reducing generated tokens, shortening reasoning for easy instances without sacrificing performance on difficult ones.

cs.AI↗

arXiv2026

UMR: Universal Manipulation Representation

General-purpose embodied manipulation hinges on a unified action representation that generalizes across embodiments and scales readily. Yet existing policies rely on embodiment-specific action spaces, making cross-embodiment demonstrations difficult to leverage at scale and limiting transfer to new embodiments and spatial variations. To this end, we introduce Universal Manipulation Representation (UMR), a unified action representation that enables zero-shot skill transfer from human demonstrations to heterogeneous robots. UMR decomposes manipulation into two functionally distinct yet geometrically linked components: embodiment-agnostic World Flow, which describes task-relevant object motion in the world frame, and Ego Trajectory, which represents end-effector motion relative to the current pose. We instantiate UMR as World--Ego Point VLA (WEPVLA), a compact 0.5B-parameter policy that learns in the unified geometric action space through a dual-stream Point Action Adapter and a unified Point Action Expert, with an $SE(3)$ conjugation coupling the two components. To improve data efficiency, we complement UMR with a Data-Efficient Strategy (DES) that diversifies object configurations through stage-aware point-cloud editing while preserving demonstrated contact geometry. In simulation, WEPVLA achieves average success rates of 97.5\% on LIBERO and 85.7\% on the 10-task RLBench benchmark. In real-world experiments, a single policy trained on human demonstrations augmented by DES transfers zero-shot to diverse deployment conditions. With about 10 minutes of collected human demonstrations per task and no robot demonstrations, it achieves 91.7\% average success across six evaluation settings, compared with 60.8\% for HumanEgo. Code and additional materials are available at https://umr-wepvla.github.io/.

cs.RO↗

arXiv2026

Finding the Right Fit: Model-Harness Interactions across Agent Tasks

Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing stays strong when the setting changes. We evaluate 66 configurations: four configurable harnesses (OpenHands, DeepSeek Harness, PI, and openJiuwen) paired with five models on TUA-Bench, ALE-CLI, and Terminal-Bench 4, plus the native Codex-GPT and Claude Code-Claude pairings. Model rankings reverse across harnesses. On Terminal-Bench 4, Claude leads GPT by 7.94 points in OpenHands but trails it by 30.16 points in PI. For four of the five models, the best harness changes from one benchmark to another, yet some pairings hold: openJiuwen gives Kimi its highest score on all three benchmarks, by 5.61 to 11.11 points. A model's own vendor harness is not reliably its best, and higher cost does not reliably buy a higher score. On Terminal-Bench 4, GPT scores higher under PI than under DSH at less than a quarter of the cost per task. Matched trajectories suggest why fit varies. Models start almost all repairs themselves, so much depends on whether the harness hands failures back in a form the model can use. GPT does best with PI's lean scaffold, while Kimi, which often issues malformed tool calls, does best in openJiuwen. We argue that the model, the harness, and the task should be evaluated together, and we release the harness adapters, evaluation code, and all 6,204 scored trajectories at https://github.com/liyix/finding-the-right-fit and https://huggingface.co/datasets/yixuanli97/finding-the-right-fit.

cs.AI↗

arXiv2026

HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models

Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies. We present Hyperbolic Clinical Ontology Embeddings (HCOE) for hierarchy-aware clinical concept representation. HCOE maps frozen BioBERT embeddings into a Poincare ball, combining parent-side and child-side ontology-guided contrastive learning with coarse-to-fine ontology-path aggregation. It uses International Classification of Diseases (ICD) codes organized by Clinical Classifications Software (CCS) and Anatomical Therapeutic Chemical (ATC) medication hierarchies. Evaluations show that HCOE performs best on ICD/ATC clinical relation prediction and CCS-to-PheCode hierarchy transfer. On the MIMIC-IV dataset, HCOE also achieves the best performance on mortality prediction, readmission prediction, medication recommendation, and rare drug prediction.

cs.AI↗

arXiv2026

STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification

Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two sources of this instability: noisy gradients produced from already-correct examples and over-specialization to hard cases that degrades performance on simpler inputs. We introduce STEVE, a stabilization framework with two coupled mechanisms. Error-Driven Refinement generates gradients only from incorrectly handled examples, concentrating updates on informative failures. Regularized Verification treats every update as provisional and accepts it only when improvement on hard cases does not cause unacceptable regression on a preservation set. Across ten reasoning benchmarks, three evaluator/optimizer models, and established prompt-optimization baselines, STEVE reduces degradation and produces more robust prompts. Additional evaluations with gpt-5.4-mini/gpt-5.4 on symbolic reasoning, GSM8K-Platinum, and DS-1000 show that these gains persist with newer models and larger test sets. STEVE therefore provides a practical way to improve the stability and effectiveness of textual-gradient prompt optimization.

cs.CL↗

arXiv2026

In-Context Robot Learning with VLM Agents

Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters? We introduce GPT-Policy, a general-agent framework for in-context robot learning. GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome. We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations. In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment.

cs.CV↗

arXiv2026

DiVA: Enabling Interactive Digital Life Simulation via Video Models

We present DiVA, a deeply interactive digital life simulator pioneering a new paradigm for long-term, open-ended interactive experiences within digital character worlds. DiVA's architecture pairs a Multimodal Large Language Model (MLLM) as a router with a meticulously designed stacked video pipeline for seamless, multi-turn interactions with action and audio response. To maintain continuity and avoid degradation, we model generation as a three-part coupled system: waiting video, action video, and the transitions between them. These transitions are critically handled by our Anchored Video Continuation (AVC) module, which returns the character to stable states to prevent degradation. By encoding information from the preceding action video segment, AVC ensures smooth transitions, significantly reducing camera jitter and inconsistencies common in current video transition methods. This design also enables complex pose changes (e.g., sitting to standing) typically difficult for audio-driven models. These system designs together ensure high-fidelity identity, coherence, and dynamics for extended experiences. To validate our pipeline design, we comprehensively compare our system against alternatives by replacing our core generation module with mainstream long-video, continuation, and interpolation methods. We further analyze the necessity of the three-stage design, anchor-state selection, transition naturalness, spatial grounding, and the quality-latency trade-off, and we expand the comparison to additional long-form audio-driven avatar models. Results confirm DiVA is markedly superior in maintaining long-term visual quality and realism, validating its effectiveness as a sustainable, interactive simulation.

cs.CV↗