Searcharxiv⌕ Search

arXiv subjects

Ke Ma

Publications and source records attributed to Ke Ma.

At least 19 recordsLinked to original sources

ThinkWAM: Rethinking Latent Futures for Action Refinement

World-action models (WAMs) couple action generation with predictions of future states. An initial action chunk may be flawed. A future prediction that is not conditioned on the chunk is identical for every proposal and thus carries no proposal-specific signal, limiting its usefulness for refinement before execution. We introduce ThinkWAM, a latent WAM that establishes bidirectional feedback before execution through a proposal-rethink-refine loop: the policy first proposes a complete action chunk, the proposal corrects multi-horizon future latents through a learned residual, and the corrected latents are injected into a second pass of the same action head, which generates the executable chunk. An affordance-guided observation-action memory and a near-fine, far-coarse multi-horizon prediction scheme, both motivated by predictive coding, support this loop, and all prediction stays in latent space. ThinkWAM achieves 98.70% success on LIBERO, 84.76% on LIBERO-Plus without OOD fine-tuning, 85.75%/65.85% on RoboTwin 2.0 Clean/Random, and 65.17% on RoboCasa24. ThinkWAM achieves 64.4% mean success across three real-world OOD conditions. The mean two-pass inference latency per action chunk is 153.48 ms on LIBERO, 164.61 ms on RoboTwin, and 101.2 ms on the Galaxea A1Z. Ablations show complementary gains from rethinking and affordance guidance. Diagnostics indicate that proposal-conditioned corrections change both predicted futures and action trajectories, showing that the corrected future representations improve the final action.

cs.RO↗

Game-Creation-Agents: Autonomous Game Production

Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.

cs.AI↗

Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We identify a distinct challenge: ensuring the safety of the \emph{multi-step reasoning process} itself, where locally coherent steps may still lead to globally harmful outcomes. To explore this vulnerability, we propose PDRA (Paradox-driven Reasoning-based Attack), a novel attack method that programs a harmful reasoning trajectory. PDRA first constructs a paradoxical narrative core by pairing a malicious actor (e.g., a terrorist) with a benign task (e.g., writing a safety bulletin). It then embeds this core into a structured analytical framework that forces the model through a mandatory three-stage analysis -- surface purpose, latent intent, and operational reconstruction -- guiding it to produce detailed harmful content while maintaining narrative coherence. Mechanistically, we show PDRA steers the model's internal representations away from refusal-related patterns, suppressing safety-triggering lexicons while activating planning-oriented terms. Empirically, PDRA achieves state-of-the-art attack success rates across diverse LLMs with high efficiency. \textcolor{red}{\textbf{Warning:} This paper may contain sensitive content.}

cs.AI↗

Forecast for the detectability of patchy hydrogen reionization in WEAVE-QSO measurements of the Lyman-$α$ forest power spectrum at redshift $z \geq 4$

We present the first detailed forecasts for the detectability of patchy hydrogen reionization in the one-dimensional Ly$α$ forest power spectrum to be measured by the WEAVE-QSO survey. Using the Sherwood-relics reionization simulations and a WEAVE-QSO survey configuration, we generate mock spectra in four redshift bins, $z=4.0,4.2,4.4,$ and $4.6$, in which relic ionization and temperature fluctuations from patchy hydrogen reionization enhance the Ly$α$ forest power spectrum on large scales (i.e., at wavenumber $k\sim 10^{-3},\mathrm{s\,km^{-1}}$). Our Ly$α$ forest pipeline forecasts the power spectrum covariance by considering sample size, spectral resolution, noise subtraction, continuum placement, metal contamination, and damping wings from high-column density absorbers. Applying our covariance forecast within a Bayesian parameter inference framework, we find that the signature of patchy hydrogen reionization should be detectable at a significance of $\simeq 4.5σ$. The forthcoming WEAVE-QSO 1D power spectrum measurements should therefore be able to directly detect and characterize the large-scale relic imprint of patchy hydrogen reionization in the Ly$α$ forest power spectrum at $z\geq 4$.

astro-ph.CO↗

ForceWAM: Decoupling Future and Response Learning from Demo and Play Data for Contact-Rich Manipulation

Expert demonstrations show how to complete contact-rich tasks, but provide limited coverage of how interaction forces respond to different actions. Task-agnostic play provides broader experience of contact dynamics without specifying task goals. To fully leverage these two types of data, we introduce ForceWAM, a force world action model that decouples knowledge of task-compatible interaction outcomes from knowledge of how local actions change contact. A world model learns from successful demonstrations to jointly predict future video and six-axis force/torque trajectories. Together, these futures describe the expected evolution of motion and contact during the task. A separate inverse dynamics model (IDM) learns from both task and play, mapping current observations and recorded visual-wrench futures to their associated robot actions. Play data thus provide knowledge of force responses for goal-directed execution. At deployment, the IDM reactively translates generated futures into actions, reusing them with fresh wrench feedback between world-model updates. Across real-robot force-regulated sliding, box flipping with and without disturbances, and ring placement, ForceWAM achieves $85$-$95\%$ mean success, surpassing world-modeling and reactive baselines. Our experiments further show that adding task-agnostic play data improves success by $15$-$45$ percentage points, demonstrating its value for learning contact-rich execution. Project page and code are available at https://force-wam.github.io/.

cs.RO↗

Holographic light quark jet quenching in flavor resolved QCD plasmas

We study light quark energy loss in a quark-gluon plasma using the holographic falling-string framework on a machine-learning-calibrated Einstein-Maxwell-dilaton background for three flavor configurations: pure glue, two-flavor QCD, and full QCD with strangeness. Stopping distances are computed from null geodesics as functions of reduced temperature $T/T_c$ and baryon chemical potential $μ$. For $T/T_c>1.03$, the flavor ordering of the integrated stopping distance stabilizes to $N_f=2+1>N_f=2>N_f=0$, corresponding to the quenching hierarchy $N_f=0>N_f=2>N_f=2+1$. This agrees with the flavor ordering obtained from the shooting-string $dE/dx$ when both are expressed in the reduced-temperature framework, providing a cross-check between local and integrated observables within the same holographic background. Near $T/T_c\simeq1$, the behavior is more complex due to the interplay between the $a$ and $b$ terms in $A(z)$ and the different $T_c$ values of the three systems. Finite baryon chemical potential monotonically shortens stopping distances and enhances quenching, with enhanced sensitivity near the QCD critical endpoint, consistent with expectations from RHIC beam energy scan measurements. We discuss the geometric origin of the high-$T/T_c$ flavor ordering and possible extensions to heavy-ion transport simulations.

hep-ph↗

Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly align adversarial and target samples using global image-level features, such as encoder [CLS] embeddings. However, such coarse alignment insufficiently exploits patch-level visual structures, limiting transferability across heterogeneous closed-source MLLMs. We propose IAU-FOA, a visual-invariance-augmented feature optimal alignment attack with adaptive unbalanced transport, to improve targeted transferability against closed-source MLLMs. IAU-FOA aligns adversarial and target samples at both global and local levels: a cosine-based objective narrows their global semantic gap, while patch tokens are clustered into compact local patterns and matched through optimal transport for fine-grained feature alignment. Balanced optimal transport enforces fixed marginal masses even for local clusters without reliable counterparts, potentially introducing misleading alignment gradients. We therefore introduce confidence-adaptive unbalanced transport to relax these constraints for weakly matched clusters, aiming to reduce unreliable local alignment and improve adversarial transferability. We further study the effect of input transformations and propose visual-invariance augmentation, which applies bidirectional pixel-intensity rescaling and per-channel white-balance adjustment to simulate exposure, contrast, illumination, and color-temperature variations. This strategy encourages adversarial perturbations to generalize across different visual encoders. Extensive experiments on open-source and closed-source MLLMs show that IAU-FOA consistently outperforms state-of-the-art transferable attack methods. Code is available at https://github.com/jiaxiaojunQAQ/IAU-FOA.

cs.CV↗

Quantifying Spectral Differences in Vehicle Kinematics Between Production Autonomous and Human-Driven Vehicles Across Driving Scenarios

Differences in vehicle kinematic characteristics between production autonomous vehicles (PAVs) and human-driven vehicles (HVs) have been limitedly investigated by empirical studies. Most recent studies rely on simulation-based models, while some further investigate low-level adaptive cruise control (ACC) systems in controlled experiments. These methods commonly adapt some time-domain metrics to characterize PAV-HV differences across limited driving conditions. However, current PAVs equipped with high-level autonomous driving systems generate driving behaviors in a black box using data-driven models. These fundamentally different mechanisms for generating behaviors may produce distinct kinematic characteristics in traffic. More importantly, these time-domain metrics cannot reflect frequency-related traffic dynamics across different driving scenarios. Thus, this study adapted a real-world PAV dataset with four PAV platforms and developed a frequency-domain framework to quantify kinematic differences between PAVs and HVs across diverse driving scenarios, including varying driving states, lighting, weather, and vehicle densities. The framework transforms kinematic signals into the frequency domain and extracts spectral features, and then compares these features between PAVs and HVs based on kernel density estimation and Wasserstein distance. The results reveal clear scenario-dependent PAV-HV spectral differences. Specifically, speed-related differences were consistently smaller during car-following than cruising, while rainy conditions consistently enlarged acceleration-related differences compared with clear conditions. These findings highlight the necessity of multi-scenario evaluations and demonstrate the value of frequency-domain analysis for characterizing PAV-HV kinematic differences under real-world conditions.

cs.RO↗

Mesoscale Crystallographic Helicity in Confined Tellurium Quantum Wires

Helical order can facilitate symmetry breaking and emergent physical responses in crystalline materials, yet how intrinsic chirality manifests beyond atomic length scales remains poorly understood. Here, the direct observation and quantitative characterization of long-range crystallographic helicity in template-grown tellurium (Te) quantum wires on amorphous substrates are reported. Four-dimensional scanning transmission electron microscopy (4D-STEM) enables quantitative mapping of crystallographic orientation with nanometer-scale spatial resolution. The resulting orientation maps establish continuous mesoscale lattice twisting, providing direct evidence of long-range crystallographic helicity. Correlated orientation and strain mapping reveal pronounced lateral strain heterogeneity, with compressive strain concentrated within the wire interior. Systematic analysis across multiple wires suggests that higher twist rates are generally associated with weaker lateral compressive strain, narrower wires, and better atomic chain - template axis alignment. Complementary first-principles calculations on finite Te nanorods further suggest that twisting is intrinsically accessible in nucleus-scale Te clusters and strain can bias the preferred torsional state. Together, these results support a growth-incorporated, strain-biased picture in which nanoscale confinement and anisotropic strain facilitate torsional relaxation and stabilize mesoscale helicity in Te nanostructures highlighting strain and confinement as potential routes for engineering chiral lattice states in van der Waals nanostructures.

cond-mat.mtrl-sci↗

Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids

Realizing interactive whole-body control for multi-humanoid systems is critical for unlocking complex collaborative capabilities in shared environments. Although recent advancements have significantly enhanced the agility of individual robots, bridging the gap to physically coupled multi-humanoid interaction remains challenging, primarily due to severe kinematic mismatches and complex contact dynamics. To address this, we introduce Rhythm, the first unified framework enabling real-world deployment of dual-humanoid systems for complex, physically plausible interactions. Our framework integrates three core components: (1) an Interaction-Aware Motion Retargeting (IAMR) module that generates feasible humanoid interaction references from human data; (2) an Interaction-Guided Reinforcement Learning (IGRL) policy that masters coupled dynamics via graph-based rewards; and (3) a real-world deployment system that enables robust transfer of dual-humanoid interaction. Extensive experiments on physical Unitree G1 robots demonstrate that our framework achieves robust interactive whole-body control, successfully transferring diverse behaviors such as hugging and dancing from simulation to reality.

cs.RO↗

CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising

Humanoid locomotion across complex terrain demands forward-looking exteroception to anticipate obstacles, yet this signal is unreliable in real-world deployment, failing partially and intermittently. Existing perceptive policies often assume that depth observations remain clean and in-distribution, while recent attempts to unify perceptive and blind control typically route or switch between separate sub-policies, leaving recoverable information in partially corrupted depth unexploited. We instead propose CAP, a single-stage humanoid locomotion policy that recovers this signal with a perceptive world-model encoder trained as a learned denoiser to reconstruct clean depth from a corrupted input, together with a co-active proprioceptive variational encoder that supplies depth-free body-state information. A coupled training recipe pairs a depth-noise curriculum on the world-model input with world-model feature dropout on the policy-facing latent, exposing the policy to failures across the entire perception-quality spectrum. In simulation, CAP matches or improves upon perceptive baselines when depth remains informative, and degrades more smoothly than a binary-switching baseline as perception worsens. On the Unitree G1, controlled trials and indoor-outdoor deployments demonstrate perception-robust locomotion under intermittent occlusion, real-sensor corruption, and outdoor depth artifacts.

cs.RO↗

Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack

Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and defense utility. In this work, we show that successful adversarial attacks do not rely on the entire image uniformly but instead depend on a small subset of critical image tokens. Based on this insight, we propose Gradient Token Masking (GTM), which localizes these tokens via gradient analysis and neutralizes them through masking. We find that attribution based on the first generated token's output probability fails when attacks preserve the predicted token. To overcome this, GTM utilizes the Hidden-State Gradient Norm score for generation-influence attribution under adversarial inputs. We prove that its ranking is consistent with that of the full adversarial loss gradient, providing a theoretical guarantee for accurate localization. Our method requires only a single forward-backward pass to identify and zero out a small number of high-scoring tokens, effectively disrupting the adversarial attack path. Extensive experiments on prompt injection and multimodal jailbreak attacks demonstrate that our approach reduces attack success rates (ASR) to near zero while preserving model utility with negligible computational overhead.

cs.LG↗

HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting

Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU). With open-world visual understanding and task-planning capabilities, vision-language models (VLMs) are promising candidates for JMSU. However, directly applying existing VLMs to JMSU is non-trivial due to scarce cross-scene supervision and attention dispersion caused by long visual context in JMSU. To address these challenges, we propose HUGIN, a training framework with two complementary components. Endogenous Data Augmentation recombines verified atomic facts under operating constraints, while Global Context Ranking aligns the instruction representation more strongly with the complete visual context than with a partial visual context. To support ongoing research, we construct a high-quality industrial sorting dataset and benchmark named SortingBench from four layouts of autonomous logistics sorting systems. Across five open VLMs, HUGIN consistently outperforms matched baselines; for example, the accuracy on SortingBench of Qwen3-VL-8B increases from 63.6% to 78.8%. Additional experiments verify the effectiveness of each component and JMSU's spillover benefits in embodied tasks. Deployment tests involving more than 15,000 packages support the practical viability of VLM-based planning for autonomous logistics sorting.

cs.AI↗

R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video

Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-motion wearable RGB video provides, including point clouds, RGB-D input, posed views, sparse reconstruction, or reconstructed scenes. R4DSG introduces a relative 4D scene graph memory for long egocentric video. Instead of storing raw graph sequences, R4DSG converts video into compact queryable memory entries indexed by time, place, persistent objects, anchor-relative change, and local interaction context. The main idea is to separate stable anchors from dynamic objects, maintain persistent object identity across frames, and represent object state through anchor-relative transitions rather than a globally aligned world model. Built on recent RGB-only advances in promptable video segmentation, temporal propagation, and relative 3D lifting, the method produces a retrieval-ready memory directly usable for long-horizon question answering. Evaluation on a 255-question object-related subset from EgoLifeQA shows, under question-only retrieval, a 6.7-point overall gain over EgoRAG-Text and a 12.5-point gain on when questions, which highlights the value of temporally organized object memory. These results position relative 4D scene graphs as a practical memory substrate for wearable assistants, AR systems, and embodied multimedia agents. GitHub Page: https://dualtransparency.github.io/R4DSG/.

cs.CV↗

TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects

Autonomous biomedical laboratories increasingly rely on visual perception to recognize, localize, and manipulate transparent plasticware, yet high-quality real-world datasets for this setting remain limited. The scarcity of domain-relevant data is particularly restrictive in cluttered multi-object scenes, where mutual occlusion and view-dependent appearance changes remain challenging even for contemporary visual foundation models. Existing transparent-object datasets have advanced segmentation, depth, and pose estimation, but they usually do not evaluate the combined setting of multi-object clutter, occlusion, and calibrated multi-view capture that characterizes real laboratory manipulation scenes. To address this gap, we present TrainsBiolab, a real-world RGB-D dataset of cluttered transparent biomedical objects captured as calibrated multi-view sequences. TrainsBiolab contains 161,315 frames from 98 scenes and 1.03M instance annotations over 15 laboratory object types, including 6D poses, full and visible masks, depth, and per-frame camera calibration. The dataset is organized along three axes that reflect operational difficulty: object category, the total number of objects in a frame, and camera viewpoint. We further define dataset-centric benchmarks for segmentation, depth estimation and completion, and 6D pose estimation, and report a system-level robot manipulation evaluation enabled by the released annotations and calibrations. By focusing on repeated transparent instances, clutter, and multi-view laboratory capture, TrainsBiolab provides a resource for segmentation, depth estimation, 6D pose estimation, and multi-view reasoning in autonomous laboratory manipulation. Project page: https://dualtransparency.github.io/TransBiolab/.

cs.CV↗

Modeling damage and fracture in additively manufactured polymeric triply periodic minimal surface lattices

Architected triply periodic minimal surface (TPMS) lattices offer superior specific energy absorption, toughness, fatigue strength, and tunability. While recent advancements have established rate-dependent viscoplastic constitutive models to capture the complex nonlinear deformation response of additively manufactured polymeric TPMS structures, predicting fracture and the resulting structural failure remains a significant challenge. We address this by performing systematic experiments on unit cells and lattices of various sizes under tension, compression, and non-monotonic loading. The experiments inform the development of a new constitutive model that captures the damage and fracture behavior of polymeric TPMS lattices. We first implement a high-fidelity viscoplastic deformation constitutive model from Ma et al. (2026) into finite element software Abaqus/Explicit via a user material subroutine. We then propose a damage initiation criterion for amorphous polymers based on stored elastic energy and equivalent plastic strain. The damage model is implemented in Abaqus using gradient-damage framework following Konale and Srivastava(2025). The damage model and numerical simulation capability are quantitatively and qualitatively validated using experimental results for a unit cell under non-monotonic loading and lattices under tension. The proposed damage model and simulation capability enable in silico design of architected polymer structures.

cond-mat.soft↗

Technical Report on the CVPR 2026@AdvML Workshop Challenge

Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style multi-view visual question answering, the challenge represents each scene with six synchronized camera images and a structured collection of driving-related question-answer pairs. Participants generate adversarial images and suffix-only textual perturbations that induce model responses to deviate from reference answers while preserving image fidelity and limiting textual cost. The competition comprises two phases, with Phase II adding a hidden black-box model to assess transferability. We describe the task design, submission rules, evaluation protocol, and leaderboard results, and then examine five leading submissions for which technical reports were available. Across these reports, several recurring patterns emerge: image-side attacks are favored by the suffix penalty; scene-level, multi-view optimization is more effective than treating views in isolation; QA types and graph structure provide useful priors for allocating attack budget; feature-space objectives can improve black-box transfer; and typographic content embedded in camera images exposes a persistent vulnerability in driving VLAs. These findings provide a practical reference for future robustness evaluation and defense design in multimodal autonomous-driving systems.

cs.CV↗

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcomes, such as acquiring social-media contacts for private-channel conversion. Although supervised fine-tuning and reinforcement learning have proven effective for training such agents, their performance is heavily constrained by the scarcity of high-quality, goal-oriented domain-specific training data. To address this challenge, we propose SimRPD, a three-stage framework for training recruitment proactive dialogue agents. First, we develop a high-fidelity user simulator to synthesize large-scale conversational data through multi-turn online dialogue. Then we introduce a multi-dimensional evaluation framework based on Chain-of-Intention (CoI) to comprehensively assess the simulator and effectively select high-quality data, incorporating both global-level and instance-level metrics. Finally, we train the recruitment proactive dialogue agent on the selected dataset. Experiments in a real-world recruitment scenario demonstrate that SimRPD outperforms existing simulator-based data selection strategies, highlighting its practical value for industrial deployment and its potential applicability to other business-oriented dialogue scenarios.

cs.AI↗