arXiv subjects

Kun Li

Publications and source records attributed to Kun Li.

At least 19 recordsLinked to original sources

arXiv2026

Keepace.ai: A Technical Report on a Large Language Model for Sports and Health

Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and rigorous evaluation benchmarks. Keepace.ai is a domain-specialized LLM built on Qwen3.5-27B through post-training, currently optimized for Chinese-language exercise guidance across three tasks: workout plan generation, sports-and-health knowledge QA, and personal sports data analysis. In internal rubric-based evaluations designed with domain experts, Keepace.ai outperforms its base model and larger general-purpose baselines, with the most pronounced improvements in exercise safety, boundary compliance, structured output completeness, and scientific accuracy. This report summarizes the current design, data pipeline, safety-first evaluation framework, and evaluation results of Keepace.ai.

cs.CL↗

arXiv2026

Open dynamics with a moving hole: inhomogeneous IFS and exponential separation condition

Let $\mathcal F=\{f_i(x)=r_i x+t_i\}_{i=0}^{b-1}$ be a self-similar iterated function system (IFS) on $\mathbb R$ with $b\ge 3$, and let $K_{\mathcal F}$ be the associated self-similar set. Given $m\in\mathbb N$, for any sequence $ω=ω^0ω^1\ldots$ with each $ω^i\in \{0,1,\ldots,b-1\}^m$ a block of length $m$, let \[ K_{\mathcal F}^ω:=π_{\mathcal F}\left(\{(d_i)\in \{0,1,\ldots,b-1\}^{\mathbb N}: d_{k+1}d_{k+2}\ldots d_{k+m}\neω^k\quad\forall k\ge 0\}\right), \] where $π_{\mathcal F}$ is the natural coding map from $\{0,1,\ldots,b-1\}^{\mathbb N}$ to $K_{\mathcal F}$. The set $K_{\mathcal F}^ω$ is called the survivor set of an open dynamical system with a moving hole related to $ω$. When $\mathcal F$ is a homogeneous IFS satisfying the open set condition (OSC), the dimensions of $K_{\mathcal F}^ω$ were determined by the first author, Sun and Wang (Adv. Math., 2026). In this paper we generalize these results to inhomogeneous IFSs. When $\mathcal F$ satisfies the OSC, we give explicit formulae for the dimensions of $K_{\mathcal F}^ω$. In particular, we show that the packing dimension and upper box-counting dimension of $K_{\mathcal F}^ω$ always coincide, while the Hausdorff dimension and lower box-counting dimension of $K_{\mathcal F}^ω$ are not necessarily equal, which is different from the homogeneous case. Furthermore, when $\mathcal F$ satisfies the exponential separation condition and the similarity dimension $s_{\mathcal F}\le 1$, we are able to determine the Hausdorff dimension of $K_{\mathcal F}^ω$. Finally, we apply our results to badly approximable numbers and non-recurrence points in the setting of inhomogeneous IFS satisfying the OSC.

math.DS↗

arXiv2026

AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution

High-fidelity atomistic evolution over long timescales requires more than observing the current crystal configuration. Instantaneous atomistic snapshots are often incomplete: locally similar configurations can correspond to different hidden dynamical contexts, future event preferences, and waiting-time scales. We argue that this snapshot ambiguity makes long-horizon atomistic evolution fundamentally a memory-based world-state restoration problem. To address this, we introduce AtomWorld-Mem, a memory-restored atomistic world model that recovers the latent world state missing from instantaneous crystal snapshots. AtomWorld-Mem treats the evolving alloy as an AtomWorld: spatial encoders write multi-scale atomistic keyframes from dense local topology and sparse long-range defect context, while short-term event memory and long-term structural memory integrate these keyframes across time to restore a future-predictive evolutionary state. The restored state is used to prioritize legal vacancy-mediated events under single-event Kinetic Monte Carlo (KMC) constraints, while event legality, physical execution, and residence-time updates remain governed by the underlying simulator. Empirically, AtomWorld-Mem improves long-horizon atomistic progress under fixed microscopic event budgets while maintaining high-fidelity evolution across energetic, structural, and vacancy-transport observables. It further transfers zero-shot across diverse unseen alloy-temperature AtomWorlds, suggesting that the learned memory-restoration mechanism captures reusable principles of hidden-state inference rather than a system-specific local energy heuristic. These results position memory-restored world-state modeling as a promising route toward efficient, physically grounded, and transferable atomistic evolution.

cs.AI↗

arXiv2026

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.

cs.AI↗

arXiv2026

SocialCoAct: Enabling and Benchmarking Egocentric Social Co-Action for VLM-Based Humanoid Robots

Enabling humanoid robots to participate effectively in social interactions is important for their integration into human-centered environments. Existing methods, however, typically map pre-generated speech directly to continuous motion trajectories but have limited awareness of complex social environments and lack explicit high-level semantic action planning. We introduce SocialCoAct, a unified agent-centered framework for VLM-based egocentric social co-action. We formulate egocentric social co-action as an end-to-end agent task and develop SocialCoAct-Agent, which transforms egocentric observations and dialogue history into verbal responses and atomic action sequences, aligns each action with its corresponding utterance span, and executes the resulting behaviors in MuJoCo and on a physical humanoid robot. To evaluate the VLM capabilities required by this task, we construct SocialCoAct-Bench from continuous egocentric recordings of natural multi-party interactions. The benchmark comprises 423 human-verified multiple-choice questions across three subtasks: Long Episode Understanding (LEU), Speaker Intention Understanding (SIU), and Coordinated Action Planning (CAP). Across a diverse set of closed-source and open-weight VLMs, including general and egocentric models, the highest overall accuracy is 77.54%, while accuracy on the hard subset reaches only 46.51%. Extended reasoning improves Qwen3-VL-2B and Qwen3-VL-4B by 19.62 and 17.02 percentage points, respectively, but reduces inference throughput by 53.6$\times$ and 20.2$\times$. Visual-input ablations further show that the benefits of visual context vary across models. SocialCoAct provides a foundation for developing and evaluating VLM-based humanoid agents that coordinate context-aware speech and action in complex social interactions. The codebase and benchmark will be made publicly available upon publication.

cs.RO↗

arXiv2026

PrismStencil: Transforming Stencil Computations into Matrix Multiplications

Stencil computations are a fundamental class of workloads in scientific and engineering applications. Although Tensor Cores offer new opportunities for stencil acceleration, existing tensorization methods suffer from substantial redundant computation and insufficient data reuse. We propose PrismStencil, a stencil tensorization algorithm that introduces a novel mapping scheme between matrices and stencil grid points. PrismStencil employs multidimensional vector mapping to accommodate the multidimensional data dependencies of stencil computations and a unified gather--scatter tensorization scheme to exploit the relative sizes of the matrix dimensions in Tensor Core operations, thereby reducing the redundant computation introduced by tensorization. Moreover, it introduces a cross-product data-reuse mechanism that exploits the overlap among neighboring stencil updates to further enhance data reuse. Across representative stencil kernels on an NVIDIA A100 GPU, PrismStencil achieves average speedups of 2.13x and 2.17x over state-of-the-art Tensor Core stencil methods with FP64 and TF32 precision, respectively.

cs.PF↗

arXiv2026

Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models

Video reward models are central to aligning video diffusion models with human preferences, yet existing ones are external vision-language models that score clean, decoded pixels. Scoring an intermediate denoising state therefore requires either finishing the remaining denoising steps or decoding a noisy latent that the reward model cannot reliably interpret. We ask whether a video generator can itself act as the evaluator, discriminating human preferences directly from its noisy latents. We propose PRISM (Preference Representation in Intermediate States of Diffusion Models), a latent video reward model that keeps a pre-trained video diffusion transformer frozen, reads features from its early blocks, and maps them to a timestep-conditioned reward through a lightweight query-based aggregation head with only 21.8M trainable parameters. PRISM outperforms pixel-space reward models at high noise levels on two benchmarks while remaining competitive with 8B-parameter vision-language reward models on clean videos. This noise robustness enables early-stage Best-of-N sampling: selecting among candidates after only a few denoising steps reduces sampling cost by up to 10x and surpasses the strongest pixel-space baseline on each generator at 3-4x lower cost.

cs.CV↗

arXiv2026

SIMPLE: Semantic Structure-Aligned Prompt Learning for Open-Vocabulary Audio-Visual Event Localization

Open-vocabulary audio-visual event localization aims to infer explicit segment-level categories for both seen and unseen audio-visual events. Existing solutions rely heavily on hand-crafted prompt templates, whose predictions are highly sensitive to subtle wording variations. Learnable prompts remove this manual tuning burden, but when trained solely on seen events, they tend to overfit to seen categories and distort the inter-event semantic topology required for generalization to unseen categories, a failure we term semantic topology drift. In this paper, we propose SIMPLE, a semantic structure-aligned prompt learning framework that aligns cross-category semantic topology between learnable and hand-crafted prompts across asynchronous audio and visual streams. Specifically, our SIMPLE combines Learnable Continuous Prompt Tuning (LCPT) with Semantic Topology Consistency Regularization (STCR). The LCPT automates prompt engineering through data-driven optimization, while the STCR module aligns the category-wise similarity distributions of learnable and hand-crafted prompts under random category subset sampling to alleviate semantic topology drift. Comprehensive experiments and analyses on the OV-AVEBench demonstrate that our SIMPLE framework achieves state-of-the-art performance on the seen and unseen splits, while using roughly half the trainable parameters and roughly one-third the training time.

cs.MM↗

arXiv2026

AtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics

Atomistic simulation is a fundamental tool for studying long-term materials evolution, from diffusion and defect dynamics to interfacial reactions and fracture. Yet conventional simulators typically advance at microscopic resolution, spending substantial computation on low-impact local updates before reaching structurally consequential states, an evolutionary-resolution bottleneck that limits long-horizon simulation. We propose AtomWorld-Mirror, a time-aware macro-step world model for the critical evolution backbone of atomic systems. For Step-Wise atomistic simulation, AtomWorld-Mirror distills short micro-event segments into physically reachable transitions between key states, jointly predicting sparse structural edits and accumulated physical time through latent macro-step dynamics. Local reachability, inventory conservation, and continuous-time consistency constrain each transition. By amortizing local atomic physics into a reusable latent macro model and replacing explicit micro-event replay with macro-step inference, this formulation provides a path toward substantially faster prediction of long-term materials evolution while preserving structural validity and time semantics. Across five atomic systems, spanning Cu-rich RPV steel irradiation aging, Cu-Zr metallic glass, and Li$_3$N-based anti-perovskite solid electrolyte, macro-step inference delivers a speed up of $10^3$ to $10^4$ times over event-by-event simulation.

cs.AI↗

arXiv2026

Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination

Multi-human cooperative object manipulation is a highly challenging topic in humanoid control. While existing methods can handle simple collaborative carrying tasks, they struggle with role-dependent, long-horizon, and sequential cooperative manipulation. To address this issue, we propose a hierarchical commander-executor framework that enables multiple agents to accomplish complex collaborative tasks in distinct ways. Specifically, a commander combines instructions and scene information for joint semantic and geometric planning. It then decomposes the task into role-specific subtasks and generates shared object-centric coordination plans, specifying execution timing, target positions, and manipulation actions for each agent. Conditioned on the commander's high-level strategy and each agent's local observations, the executor learns a low-level physics-based policy through a solo-to-cooperative curriculum to realize coordinated human-object interactions. The planned object trajectory provides a shared coordination target, while root positions and grasping instructions specify role-dependent execution cues. We evaluate our method on a variety of object manipulation tasks, demonstrating its ability to execute long-horizon tasks that combine different types of collaboration and to scale from two-agent to multi-agent cooperation. Extensive experiments further show that our approach achieves higher success rates compared to state-of-the-art methods. Code will be made publicly available at https://github.com/TJU-3DV/Co-Manipulation.

cs.RO↗

arXiv2026

Talk, Render, Act: Integrating Social Gesture and Digital Face with Synchronized Speech for Conversational Humanoid Robot

Expressive humanoid interaction requires speech, facial animation, and body gestures to form a coherent response. However, many full-body humanoid robots produce speech and gestures without a visually expressive face, while talking-face animation and robot gesture generation are typically developed separately. We present Talk, Render, Act (TRABot), an agent-based framework comprising specialized agents for motion-atom construction, dialogue generation, motion planning, and facial animation. First, to produce natural and semantically meaningful gestures, we construct Robot-Ready Semantic Motion Atoms by segmenting long-form, G1-retargeted BEAT2 motion into units with natural gesture boundaries, human-verified communicative functions, and feasible trajectories. Second, to preserve semantic order and coordinate body motion with the spoken response, we introduce a Semantic-Conditioned Compositional Planner. Given an ordered semantic function sequence and an estimated response duration, the planner selects approved atoms to realize the longest feasible action sequence while accounting for transitions and neutral recovery. Finally, we deploy a Streaming Face-Speech-Body Integration system on a physical G1 humanoid, combining streaming dialogue audio, audio-driven facial animation, and semantically planned body motion in a unified real-time interaction loop. Quantitative and qualitative experiments demonstrate that TRAbot achieves the best overall performance among all compared conditions in terms of naturalness, expressiveness, and multimodal coherence.

cs.RO↗

arXiv2026

Query-Guided Spatial-Temporal-Frequency Interaction for Music Audio-Visual Question Answering

Audio--Visual Question Answering (AVQA) is a challenging multimodal task that requires jointly reasoning over audio, visual, and textual information in a given video to answer natural language questions. Inspired by recent advances in Video QA, many existing AVQA approaches primarily focus on visual information processing, leveraging pre-trained models to extract object-level and motion-level representations. However, in those methods, the audio input is primarily treated as complementary to video analysis, and the textual question information contributes minimally to audio--visual understanding, as it is typically integrated only in the final stages of reasoning. To address these limitations, we propose a novel Query-guided Spatial--Temporal--Frequency (QSTar) interaction method, which effectively incorporates question-guided clues and exploits the distinctive frequency-domain characteristics of audio signals, alongside spatial and temporal perception, to enhance audio--visual understanding. Furthermore, we introduce a Query Context Reasoning (QCR) block inspired by prompting, which guides the model to focus more precisely on semantically relevant audio and visual features. Extensive experiments conducted on two AVQA benchmarks demonstrate the effectiveness of our proposed method, achieving significant performance improvements over existing Audio QA, Visual QA, Video QA, and AVQA approaches. The code is released under https://github.com/lik1996/QSTar.

cs.CV↗

arXiv2026

Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation

Referring Audio--Visual Segmentation (Ref-AVS) is an emergent multimodal task requiring the precise identification and segmentation of a specific object based on a natural language expression grounded in both visual and auditory cues. Unlike traditional AVS, which segments generic sound sources, or referring video object segmentation (Ref-VOS), which relies solely on visual--textual grounding, Ref-AVS necessitates fine-grained tri-modal interaction across vision, audio, and language. However, existing methods often fail to maintain consistency when subjected to target shift, a phenomenon where the model erroneously transfers its focus between objects due to transient occlusions, acoustic fading, or identity ambiguities. To address this, we propose a novel Shift-Aware Identity-guided Latent (SAIL) refinement framework. It introduces a dual-token strategy that decouples frame-level dynamics from a global semantic anchor to explicitly model target-shift cues. We design a shift-aware refinement module that rectifies drift by aligning tokens with domain-specific evidence. Finally, we leverage a decoder that integrates the refined embeddings with a continuous memory update to maintain spatio-temporal coherence and identity consistency throughout the video sequence. Extensive experiments conducted on two Ref-AVS benchmarks demonstrate the effectiveness of our proposed method, significantly outperforming existing AVS, Ref-VOS, and Ref-AVS approaches. The code will be released after publication.

cs.CV↗

arXiv2026

Spiral states, first-order transitions and specific heat multipeak phenomenon in $J_1$-$J_2$-$J_3$ Ising model: A Wang-Landau algorithm study

The classical $J_1$-$J_2$-$J_3$ Ising model on the honeycomb lattice is important for understanding frustrated magnetic phenomena in materials such as FePS$_3$ and Ba$_2$CoTeO$_6$, where diverse phases (e.g., striped, zigzag, armchair) and magnetization plateaus have been experimentally observed. To explain the experimental results, previous mean-field studies have explored its thermal phase transitions, identifying armchair phases and striped phases, but their limitations call for more reliable numerical investigations. In this work, we systematically revisit the classical $J_1$--$J_2$--$J_3$ Ising model using the Wang--Landau algorithm; in strongly frustrated parameter regimes where the Wang--Landau sampling becomes difficult, we further employ parallel tempering and a two-replica cluster algorithm combined with population annealing. We find that the armchair (AC) phase, previously reported in mean-field and experimental studies, actually coexists with the spiral (SP) phase, with their combined degeneracy reaching 20-fold (4-fold for the AC states and 16-fold for the spiral states). The phase transitions and critical exponents are studied at different interaction values. We observe first-order phase transitions, continuous phase transitions, and even the multipeak phenomenon in frustrated systems. These results clarify the nature of phases and phase transitions in frustrated Ising systems and their exponents, and additionally provide inspiration for experimental efforts to search for the spiral state and the specific-heat multipeak phenomenon.

cond-mat.str-el↗

arXiv2026

Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs

Traditional ``row-count $\times$ quality coefficient'' approaches fail to capture the nonlinear utility of data for Large Language Model (LLM) capabilities. We present a utility-aware data valuation framework that moves from static accounting toward utility-based pricing. The framework combines token-level information density and data quality, empirical training contribution estimated by influence functions, proxy models, and Data Shapley values, and cryptographic mechanisms based on hash commitments, Merkle trees, and tamper-evident training ledgers. Preliminary evaluation includes a smoke-scale multi-domain study and a synthetic duplication test. Results show that proxy-based empirical gain achieves strong ranking agreement with proxy-defined realized utility and substantially outperforms row-count and token-count baselines in the tested setting, while the prototype provides a controlled sanity check of the valuation pipeline and its sensitivity to duplication-based manipulation.

cs.LG↗

arXiv2026

EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control

Humanoid robots require whole-body motions that adapt to scene context, task requirements, and user intent. Motion tracking reproduces specified trajectories, and humanoid vision-language-action systems provide semantic interfaces, but neither offers a scalable and interactive prior for broad full-body behavior. We introduce EgoPriMo (Egocentric Motion Prior for Humanoid Robots), a unified framework that learns such priors from egocentric human demonstrations. Given egocentric observations and a text prompt, EgoPriMo reconstructs, generates, and forecasts SMPL-based full-body motion. Language is used as a high-level control signal rather than a complete motion specification. At the core of EgoPriMo is a Triple-stream DiT that jointly models body dynamics, egocentric visual context, and text; task-conditioning masks route different tasks and missing-modality data through the same checkpoint. Experiments on Nymeria and EgoExo4D show that one checkpoint improves egocentric motion generation over UniEgoMotion while supporting reconstruction and forecasting; the generated SMPL motions can also be executed by a Unitree humanoid controller. These results indicate a practical path from scalable egocentric observations to generalizable and interactive humanoid motion priors.

cs.RO↗

arXiv2026

Learning to Select Source Domains: Proxy-Rewarded Policy Optimization for Molecular OOD Generalization

Molecular property prediction under severe out-of-distribution (OOD) shifts remains challenging because conventional scaffold splits can retain local structural similarity between training and test molecules, while adaptation from heterogeneous source domains may cause negative transfer. We introduce SCOPE-Bench, a scaffold-cluster benchmark constructed by partitioning Bemis-Murcko scaffolds in an explicit physicochemical descriptor space, and POMA, a retrieve-compose-adapt framework for source-domain selection when target property labels are unavailable. POMA uses unlabeled target structures to retrieve labeled source scaffolds as proxy targets. A policy is trained from reductions in proxy-task mean absolute error after adaptation, and the selected source subset is then used for target adaptation with covariance alignment at the whole-molecule and BRICS-derived substructure levels. We evaluate HOMO, LUMO, and HOMO-LUMO gap prediction on QM9 using three 3D molecular backbones and 15 target-scaffold tasks. Relative to conventional scaffold splitting, prediction errors on SCOPE-Bench increase by up to 8.0-fold, with a mean increase of 5.9-fold. Relative to the supervised baseline under the strict OOD split, POMA reduces mean absolute error by up to 11.2%, with an average relative reduction of 6.2% over the nine backbone-property combinations. These results support adaptive source selection as a useful strategy for molecular prediction under strong structural distribution shifts.

cs.LG↗

arXiv2026

Efficient World Action Model Inference with Adaptive Intermediate States

World Action Models (WAMs) enable future-aware control by jointly modeling actions and environment dynamics. However, iterative diffusion or flow inference incurs substantial denoising latency. Prior inference state offers a natural opportunity for acceleration, yet changing planning contexts, observations, and intermediate representations can quickly render retained state stale. Preserving useful computation therefore requires adapting inference state rather than reusing it as-is. To this end, we present $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$, a training-free framework that accelerates WAM inference by preserving and adapting inference state for efficient and accurate continuation as the control loop evolves. Across closed-loop replans, Trajectory Remapping remaps replan state from the preceding replan to initialize the next replan, reducing redundant trajectory generation. Across denoising steps, Observation Rebinding performs anticipatory inference during action execution and rebinds retained denoising state to the real observation for continuation when consistency checks pass, reducing latency exposed to the control loop. Across Transformer layers, Residual Rescaling selectively rescales retained layer state and refreshes it through full computation of the middle layers when probe checks fail, reducing repeated Transformer computation. Evaluations of three representative WAM architectures on LIBERO and RoboTwin 2.0 show that $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$ achieves 1.47-3.05$\times$ speedups in observation-to-action latency and 2.23-3.27$\times$ speedups in GPU inference time per replan, while preserving 96.69-99.54% of native WAM task success.

cs.RO↗