Computation and Language
QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation
Demian Pavlyshenko and Bohdan Pavlyshenko
Functional annotation of newly sequenced
proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the
protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of
proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.
Read the full abstract ▾
Computer Vision
MIRAGE: Full-Body Bystander Privacy for Smart Glasses with Consent-Based Restoration
Muhammad Umair, Muhammad Danial Maqbool, Fatima Arshad Cheema et al. (+4 more)
Video recording on smart glasses exposes more than faces. Continuous capture reveals full-body biometric signatures, including gait, posture, and silhouette, that enable person re-identification (ReID) even after conventional face sanitization. We present MIRAGE, a three-tier architecture for
privacy-preserving smart glasses that enforces full-body
privacy, supports synthetic full-body replacement, and retains encrypted recovery material for consent-based restoration. We implement MIRAGE on a Raspberry Pi~5 (a CPU-only proxy for smart-glasses compute), companion phones, and a cloud generative backend. Compared to prior systems, MIRAGE achieves 0.948 AP and 0.976 AR while accurately detecting the complete visible body. Its bounding box masking reduces learned silhouette-based ReID to essentially random guessing, with 10.86% Rank-1 accuracy compared with an 11.12% measured chance level. Even against an adaptive adversary retrained on MIRAGE's sanitized pose signals, Rank-1 gait identification drops from 90.25% to 26.20%, removing 72.5% of the adversary's identification advantage.
Read the full abstract ▾
All authors Muhammad Umair, Muhammad Danial Maqbool, Fatima Arshad Cheema, Kapal Dev, Muhammad Hamad Alizai, Muhammad Ali Siddiqi, Naveed Anwar Bhatti
Robotics
Estimation and Control of Tensegrity Manipulator Kinematics based on Strut Inclination Angles
Tufail Ahmad Bhat and Shuhei Ikemoto
Unlike conventional rigid-link
robots defined by discrete joints, continuum
robots pose a fundamental challenge for expressing their complex continuous bending configurations for closed-loop control. Several modelling approaches have been proposed for conventional continuum
robots, but tensegrity-based continuum
robots remain largely open. Moreover, many of these approaches assume a continuous elastic backbone and are therefore not directly applicable to tensegrity manipulators, whose bodies are networks of rigid struts and tensioned cables. This work presents a reduced-order model for shape and posture control of a tensegrity-based continuum manipulator. The manipulator is modelled as a serially connected parallel-link mechanism. The proposed method is formulated as an optimization problem that uses
geometric constraints of the tensegrity structure together with information from the Inertial Measurement Unit (IMU) sensors embedded in the strut elements. To the best of our knowledge, this work presents the first experimental demonstration of a real-time IMU-based shape estimation method on a full-scale tensegrity manipulator and demonstrates posture control using a simple Proportional-Integral (PI) controller. The results show that the proposed method can estimate the shape of both single-module tensegrity structures and multi-module tensegrity manipulators from arbitrary static configurations and achieve desired postures.
Read the full abstract ▾
Human-Computer Interaction
Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations
Nicolas Leins, Jennifer Haase, Varvara Geronimus et al. (+2 more)
Simulating student personas with large
language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five
prompt-level mechanisms using separate monitoring and intervention pipelines. Across 1,200 28-turn conversations spanning four LLMs and two ADHD persona intensities, we varied when to intervene (static vs. adaptive) and what to inject (reinjection vs. reflective reminder), plus a novel adaptive condition in which a monitor generates behavior-specific instructions. Relative to no intervention, reinjection reduced the modeled rate of LLM-rated drift by 35–38%, reflective reminders by 22–27%, and behavior-specific instruction by 87%. None eliminated drift. We found no evidence that adaptive timing outperformed static scheduling. Monitoring therefore appears more useful for deciding what to correct than when to intervene, although behavior-specific instruction requires component-level testing.
Read the full abstract ▾
All authors Nicolas Leins, Jennifer Haase, Varvara Geronimus, Jana Gonnermann-Müller, Sebastian Pokutta
Computer Vision
Dynamic Thermal Gaussians: Multimodal 4D Gaussian Splatting
Rongfeng Lu, Lifeng Lin, Xiaobao Wei et al. (+7 more)
Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temperature analysis from 2D to 3D space, yet most existing works assume static temperature distributions, neglecting the temporal dynamics of heat transfer in real-world environments. To address this limitation, we propose the first dynamic RGB-Thermal reconstruction framework for complex scenes. Our method jointly models RGB appearance, thermal observations, and scene geometry as they change over time. Specifically, we introduce a
multimodal dynamic scene representation that anchors both the color and thermal modalities to a shared
geometric substrate, ensuring their consistency under spatiotemporal deformations. We further design
multimodal embeddings to enhance the motion expressiveness for each modality, and propose a
multimodal routing mechanism that retains a unified set of shared
multimodal Gaussians as the
geometric backbone while adaptively spawning modality-specific Gaussians to strengthen the representational capacity in detail-rich regions of each individual modality. In addition, we contribute a novel
benchmark dataset featuring high-frequency temperature variations to facilitate the evaluation of 4D reconstruction. Extensive experiments demonstrate that our method achieves high-fidelity spatiotemporal reconstruction of both appearance and temperature. Our code and
dataset are available at: https://github.com/LinLif1869/DTG.
Read the full abstract ▾
All authors Rongfeng Lu, Lifeng Lin, Xiaobao Wei, Quan Chen, Ming Lu, Yitian Xue, Yaoqi Sun, Yuhan Gao, Anke Xue, Chenggang Yan
Human-Computer Interaction
Finger-to-Ear ECG: Systematic Evaluation of an Earbud-Based Cardiac Monitoring Approach
Philipp Lepold, Paula Breitling, Jonas Hummel et al. (+2 more)
Ear-ECG enables unobtrusive cardiac monitoring, but existing approaches often struggle with low signal amplitudes and limited morphology preservation. We evaluate a finger-to-ear ECG paradigm that combines an in-ear electrode with a rear housing finger-contact electrode in a speaker-equipped earbud. A study with 30 participants investigated four finger-to-ear electrode geometries against chest-reference ECG and additionally assessed robustness under music playback, talking, and walking disturbances. Left-finger configurations achieved R peak detection F1-scores >99% with high agreement of key ECG morphology features. In contrast, right finger configurations as well as walking led to severe signal degradation. The results reveal a trade-off: while cross-body setups provided the highest signal fidelity, users preferred same-side contacts for comfort reasons. This establishes finger-to-ear ECG as a robust, morphology-aware paradigm for opportunistic sensing in earables.
Read the full abstract ▾
All authors Philipp Lepold, Paula Breitling, Jonas Hummel, Tobias Röddiger, Michael Beigl
Machine Learning · Cross-listed from stat.ML
Beyond Point Prediction: Artificial Representative Trees with Uncertainty
Lea L. Mairhöfer, Silke Szymczak, Björn-Hergen Laabs et al. (+1 more)
Random forests (RFs) predict well but are opaque, whereas single decision trees are interpretable but unstable. Artificial representative trees (ARTs) were developed as interpretable surrogate models for RFs, but their use as standalone prediction models with uncertainty quantification has not been systematically investigated. We combine ARTs with leaf-wise Mondrian conformal predictive systems (CPS), enabling a single tree to provide continuous predictions, prediction intervals, and probabilities of exceeding arbitrary thresholds. We compared ARTs with CPS against decision trees with CPS and separate regression and probability trees across five simulation scenarios, 21
benchmark datasets, and a cross-sectional NHANES example data set. Repeated cross-validation assessed predictive performance, interpretability, and stability. ARTs with CPS yield compact, structurally stable trees with substantially more reproducible split-variable selection than decision trees across
benchmark datasets and NHANES. Decision trees showed slightly better predictive performance and narrower prediction intervals, while coverage was broadly comparable. CPS-based trees generally achieved lower and less variable Brier scores than multi-model approaches. Combining ARTs with CPS therefore provides a single, interpretable, and stable model for continuous predictions and calibrated probabilities, balancing predictive performance with reproducibility and transparency in settings where stability and interpretability are essential.
Read the full abstract ▾
All authors Lea L. Mairhöfer, Silke Szymczak, Björn-Hergen Laabs, Tuwe Löfström-Cavallin
Computer Vision
ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination
Foundation Model and Li Auto Inc
Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and execution feedback. We introduce MachEmbodied-VLM (ME-VLM), a unified
vision-
language model with two variants, 4B and 35B-A3B, that brings together
embodied cognition and
multimodal agent capabilities. Our work emphasizes physical perception and spatiotemporal
reasoning, together with planning, interaction, and outcome assessment in both digital and physical environments. We construct training data spanning
embodied and
multimodal agent tasks, including execution observations and feedback to support outcome assessment and decision refinement. The training pipeline comprises
embodied capability injection, separate reinforcement learning of
embodied and
multimodal-
agent experts, and multi-teacher on-policy
distillation that consolidates their complementary capabilities into a single model. Experiments show competitive performance on both
embodied and
agent benchmarks, as well as on autonomous-driving and
embodied-
navigation tasks. For edge deployment, visual
token compression, W4A8 quantization, and hardware-software co-optimization enable on-device inference of the 4B variant on the M100, reducing prefill latency from 400 ms to 188 ms. Project Page: https://machembodied.com/ME-
Brain/ME-VLM.html Code Repository: https://github.com/MachEmbodied/ME-VLM
Read the full abstract ▾
Robotics
Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D
Haoxuan Li, Sixu Yan, Lianghui Zhu et al. (+3 more)
Vision-
Language-Action (VLA) models have demonstrated remarkable generalization in robotic manipulation via large-scale
multimodal pretraining. However, VLA models are mainly trained on 2D-centric observations, which inherently constrains their capacity for precise spatial manipulation. Previous methods enhance 3D awareness by introducing implicit spatial priors, but still lack explicit geometry guidance. In this paper, we propose Bridge3D that integrates both implicit and explicit 3D geometry guidance into pre-trained 2D VLA models, enabling them to ”see” and ”act” in 3D. Bridge3D introduces two strategies: 1) Implicit Fusion, which enriches visual
tokens with features from 3D foundation models to improve ”seeing” in 3D; 2) Explicit Conditioning, which integrates action denoising with an explicit 3D semantic field to achieve ”acting” in 3D. Furthermore, we utilize the proposed layer-wise linear probing to improve learning efficiency. Experiments show that Bridge3D achieves superior performance against state-of-the-art methods. On the RoboTwin 2.0
benchmark, Bridge3D exceeds $\pi_0$ by 14.0 percentage points, while in real-world experiments, it outperforms Spatial Forcing by 11.7 percentage points. These results demonstrate Bridge3D's strong capabilities in high-precision and spatial-sensitive manipulation tasks.
Read the full abstract ▾
All authors Haoxuan Li, Sixu Yan, Lianghui Zhu, Xuanlai Tang, Shikang Wang, Xinggang Wang
Computer Vision
Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma by Integrating Multimodal Ultrasound and Clinical Data: A Multicenter Study
Jun Cheng, Yuanyuan Kong, Qing Huang et al. (+9 more)
Background: Microvascular invasion (MVI) predicts recurrence and survival in hepatocellular carcinoma (HCC) but requires postoperative histopathology for diagnosis. We developed and validated a model integrating
multimodal ultrasound and clinical data for preoperative MVI prediction. Methods: This multicenter study included 489 patients with HCC from eight centers. All patients had B-mode ultrasound (BUS), color Doppler flow imaging (CDFI), dynamic contrast-enhanced ultrasound (DCE-US), and clinical information. Data from seven centers (n = 421) were used for model development with five-fold cross-validation; data from the remaining center (n = 68) formed an independent external validation cohort. The proposed
multimodal information fusion network used modality-specific encoders, a hemodynamic temporal change module for bidirectional DCE-US perfusion changes, and a representation consistency learning module to align heterogeneous ultrasound representations before
Transformer-based fusion. Results: In external validation, DCE-US achieved the highest single-modality area under the receiver operating characteristic curve (AUC; 0.8545+/-0.0198), versus clinical information (0.6715+/-0.0156), CDFI (0.6435+/-0.0344), and BUS (0.6087+/-0.0417). Pixel-difference sampling and the proposed temporal module outperformed alternative sampling and
video representation methods. The full model achieved the best performance, with an AUC of 0.8953+/-0.0180, accuracy of 81.18%+/-2.83%, sensitivity of 86.40%+/-6.69%, and specificity of 78.14%+/-6.28. Conclusions: Integrating
multimodal ultrasound and clinical information enabled promising preoperative MVI prediction in HCC. DCE-US was the main source of predictive information, while BUS, CDFI, and clinical information provided complementary value. The proposed framework may support preoperative risk stratification and individualized clinical decision-making.
Read the full abstract ▾
All authors Jun Cheng, Yuanyuan Kong, Qing Huang, Xiaotong Tan, Licong Dong, Yulong Han, Wufeng Xue, Ruobing Huang, Dong Ni, Qi Yang, Jie Yu, Ping Liang
Mathematical Software
AWE: Adaptive Weight Encoding for Exact Integer Matrix Products with Fewer GEMMs on FP4 Tensor Cores
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino et al. (+1 more)
Emulation of high-accuracy floating-point
matrix multiplication, as in the Ozaki scheme, splits the inputs into low-precision components and multiplies them pairwise. These products must be error-free, and each is an integer
matrix product times a scale factor. FP4 Tensor Cores are the fastest on the NVIDIA B200 and B300 but cannot hold INT8 operands. The FP4 values scaled by 2 form the set $S = \{0, \pm1, \pm2, \pm3, \pm4, \pm6, \pm8, \pm12\}$, which contains every residue modulo 13, so with carries any integer splits into base-13 digits that FP4 can store. Prior work splits each INT8 operand into 3 such digits (limbs) with weights $(1, 13, 169)$ and multiplies them pairwise, 9 FP4
matrix multiplications (GEMMs) for INT8$\times$INT8. The classical ways to reduce products, such as the Karatsuba and Toom–Cook methods, do not apply as they stand: sums of limbs reach $\pm 24$ and leave $S$. This paper asks how many FP4 GEMMs are needed for one integer
matrix product. We propose Adaptive Weight Encoding (AWE): the limbs take freely chosen integer weights, the stored planes are linear combinations of limbs, and the exact product is the sum of the FP4 GEMMs scaled by reconstruction coefficients. For each input range, we searched these choices for encodings with fewer products and found INT8$\times$INT8 in 6 products and INT4$\times$INT8 in 4. The formulation also holds modulo $m$, which covers the residue number systems of Ozaki scheme II: for the FP64 significand, the 75 products of prior work are reduced to 59. The boundary in product count between encodings with and without residues lies near input width 15. We release the encodings found.
Read the full abstract ▾
All authors Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri
Artificial Intelligence
Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging
Hyunjoong Cho and Jinhyeok Jang
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by exploiting low-rank structures of task-specific updates, but they commonly assign the same rank capacity to every task. This uniform allocation ignores that task vectors can have heterogeneous spectral complexity, causing the shared merging space to be used suboptimally. In this paper, we propose Spectral Energy-proportional Rank Allocation (SERA), a simple task-adaptive strategy that allocates ranks according to the singular-value energy structure of each task vector. By assigning richer spectral capacity to complex or isolated tasks and fewer directions to compact tasks, SERA extends SVD-based model merging from uniform-capacity merging to task-dependent capacity allocation. Experiments under standard
vision model merging protocols show that SERA improves multi-task merging performance while preserving the same total rank budget as existing spectral merging methods. Further analysis demonstrates that task-level spectral concentration is closely related to the per-task effect of adaptive rank allocation, providing insight into when and why SERA is effective.
Read the full abstract ▾
Computation and Language
LLJ Cards: Best practices for the Use of LLMs as Judges
Khaoula Chehbouni, Melina Medjdoub, Florian Carichon et al. (+2 more)
In recent years, large
language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these systems have been widely adopted by researchers and practitioners across a broad range of measurement tasks, driven by their strong performance, scalability, and cost-effectiveness relative to human judgment. However, a growing body of work has shown that the use of LLJs raise concerns about their validity and reliability as evaluators. Existing efforts to address these challenges have largely focused on developing bias-mitigation techniques and refining prompting strategies. While these approaches represent an important step forward, they primarily offer technical fixes and leave a more fundamental challenge unaddressed: the lack of standardized, transparent, and reproducible evaluation practices. In this paper, we introduce LLJ Cards, a framework that synthesizes best practices from measurement theory, natural
language generation, and machine learning literature into practical guidelines for LLJ-based evaluations. While LLJs offer a promising path toward scalable evaluation, their effective use requires grounding in rigorous evaluation principles to ensure validity, reliability, and reproducibility. LLJ Cards addresses this need by providing a structured framework for applying these principles in the design and reporting of automated evaluations.
Read the full abstract ▾
All authors Khaoula Chehbouni, Melina Medjdoub, Florian Carichon, Golnoosh Farnadi, Jackie Chi Kit Cheung
Cryptography and Security
Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner et al. (+22 more)
AI
agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for legal compliance, governance, accountability, and security; current frameworks must be adapted to the unique characteristics of AI
agents. In this paper, two editorial authors compare AI systems and AI
agents and, drawing on input from 23 experts in academia and industry, identify the information required for reporting incidents where the security of AI
agents is harmed. %involving AI
agents. Potential reporting elements include, for example,
agent memory and
memory accesses, actual and potential levels of autonomy, and tool usage. Based on these findings, we identify several open research questions, including how to efficiently record incidents and how to determine whether vulnerabilities and incidents generalize. Expert feedback also highlighted potential reporting weaknesses, such as risks of data leakage and attacks targeting the reporting infrastructure itself, creating additional research needs. Lastly, we summarize
privacy requirements and outline research directions for the secure and trustworthy deployment of AI
agents.
Read the full abstract ▾
All authors Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner, Battista Biggio, Nico Ebert, David Filip, Marc Fischer, Heather Frase, David Hofer, Juliane Hoffmann, Daphne Ippolito, Somesh Jha, Sean McGregor, Esfandiar Mohammadi, Luca Nannini, Cristina Nita-Rotaru, Alina Oprea, Kevin Paeth, Andrew Paverd, Jonathan Petit, Andreas Rauber, Christian Riess, John Sotiropoulos, Andreas Wespi, Kathrin Grosse
Databases
Pierce: GPU Ray Tracing for Spatial Joins over Complex 3D Data
Anton Hackl and Eleni Tzirita Zacharatou
Many emerging applications, from computational biology to digital twins and urban planning, rely heavily on three-dimensional spatial joins over polyhedral meshes. These joins comprise computationally-intensive triangle–triangle intersection tests that pairwise compare the faces of polyhedral meshes. Since each mesh may contain thousands of faces, the resulting cost challenges the responsiveness of spatial data management techniques. Existing techniques follow the filter-and-refine paradigm, accelerating either the filtering step through indexing or the refinement step through progressive mesh compression combined with GPU parallelization of triangle–triangle tests. However, the former neglects the high cost of intra-geometry refinements, whereas the latter lowers this cost but still relies on the same pairwise triangle–triangle tests. In this paper, we introduce Pierce, an approach that reformulates three-dimensional spatial joins over complex polyhedral meshes as ray-tracing operations and leverages the hardware ray-tracing units (RT cores) of modern GPUs to accelerate query execution. Our approach casts rays along the edges of one mesh against a spatial hierarchy built over the other, performing ray–node tests at the internal levels to prune distant geometries and ray–triangle tests at the leaves to identify intersecting meshes, both of which RT cores accelerate in hardware. We evaluated Pierce on real and synthetic data against multiple baselines, demonstrating more than two orders of magnitude speedup on digital pathology data compared to the state-of-the-art approach.
Read the full abstract ▾
Robotics
InsertAnything: Generalizable Contact-Rich Precision Insertion from Simulation to Reality
Zhenghua Ma, Xinpan Meng, Zeyu Liu et al. (+4 more)
Contact-rich precision insertion is a key manipulation skill in robotic assembly. Tight clearances make insertion more sensitive to
alignment errors and prone to collisions and jamming, while variations in geometry and clearance across parts further complicate policy reuse. We present a reinforcement learning framework that trains insertion policies entirely in simulation for direct deployment without real-world demonstrations or policy fine-tuning. By combining target poses with compact three-dimensional fingertip force feedback, the policy learns to search for
alignment and correct its motion despite errors in the estimated hole position. A decoupled gated reward coordinates
alignment and insertion. Force-signal smoothing and state-independent standard deviations stabilize the learning process. The resulting policies perform real-world insertion across multiple hole geometries with a minimum nominal clearance of 0.02 mm and improve success while reducing peak contact forces under hole-position errors. Cross-clearance and cross-geometry evaluations further confirm policy generalization. The system achieved the first perfect score of 20/20 on ManipulationNet's peg-in-hole
benchmark under its Human-in-the-Loop protocol, with fully autonomous insertion motions. A single policy trained only on a simulated hexagonal insertion task achieved an overall success rate of 95.0% across eight unseen real-world insertion tasks. These results show that learning entirely in simulation can yield precision insertion skills that can be deployed directly and reused across real-world tasks. The project website (https://mzhsoul.github.io/InsertAnything/) provides open-source simulation and real-
robot experiment scripts, assets, and trained checkpoints.
Read the full abstract ▾
All authors Zhenghua Ma, Xinpan Meng, Zeyu Liu, Muyuan Ma, Hengdi Zhang, Houcheng Li, Long Cheng
Computer Vision
0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation
Xiaoqiang Lu, Licheng Jiao, Lingling Li et al. (+5 more)
Recent advances in
vision foundation models (VFMs) have shown remarkable capabilities across diverse unimodal visual tasks. However, adapting VFMs to referring image
segmentation (RIS) typically necessitates precise
vision-
language alignment via full fine-tuning, incurring substantial computational overhead and risking catastrophic forgetting. While existing parameter-efficient fine-tuning (PEFT) methods enable safe knowledge transfer with minimal training costs, they predominantly operate independently within individual modalities or focus exclusively on unidirectional guidance from
language to
vision, overlooking progressive cross-modal interaction and visual feedback for textual refinement. To address these limitations, we propose $\textbf{B}$idirectional $\textbf{R}$eciprocal $\textbf{L}$earning ($\textbf{BRL}$), a novel adapter-based PEFT framework that facilitates hierarchical, bidirectional information flow within both
token-mixing and channel-mixing layers of frozen foundation models. Specifically, BRL introduces two complementary lightweight modules. The Reciprocal
Attention Adapter (RAA) performs cross-modal query-key exchanges at the
token level, enabling visual and linguistic
tokens to mutually attend to each other for fine-grained spatial grounding. The Reciprocal Gate Adapter (RGA) generates cross-modal gating signals at the channel level, allowing global semantic context from one modality to adaptively recalibrate channel activations of the other. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg
benchmarks demonstrate the superiority of BRL over prior RIS methods, achieving state-of-the-art performance while requiring less than 0.5% backbone parameter updates. Code and models will be released at https://github.com/xiaoqiang-lu/BRL.
Read the full abstract ▾
All authors Xiaoqiang Lu, Licheng Jiao, Lingling Li, Yuting Yang, Long Sun, Wenping Ma, Xu Liu, Fang Liu
Numerical Analysis
Error Analysis and Precision Selection for Mixed-Precision DEIM-CUR Decompositions
Ioannis Thanasis and Erin Carson
CUR approximation is a popular approach for constructing an interpretable low-rank approximation of a
matrix. There are many approaches for constructing the CUR approximation, many of which are based on the SVD. Results in the literature bounding the quality of the approximation usually rely on the assumption that all or part of the SVD is computed exactly. In this work, we relax this assumption and show how the quality of the approximation is affected by an inexact SVD. Moreover, we analyze the effect of finite precision arithmetic on the DEIM-CUR method. Our analysis suggests guidelines for selecting the working precisions for the SVD and the DEIM index selection
algorithm. In particular, it suggests that in many cases one can use very low precisions for these computations without significantly impacting the approximation quality. A set of numerical experiments is presented to demonstrate the theoretical results.
Read the full abstract ▾
Robotics
TACIT: Tactile Contact Supervision for Spatial Attention in Dexterous Manipulation
Yanhou Lai, Fucai Zhu, Ruiqiang Wang et al. (+1 more)
Visuomotor policies trained from a few demonstrations may reproduce demonstrated trajectories without reliably following changes in object position. Existing approaches with explicit
attention typically obtain spatial priors from human annotation or visual models. We introduce TACIT (tactile contact informs
attention), which uses measured tactile contacts from teleoperated demonstrations to supervise spatial
attention without additional point annotation. Gaussian targets over preceding camera point clouds supervise an
attention head whose pooled output conditions a visuotactile
diffusion policy. Targets are used only during training; tactile observations remain inputs at inference. In the primary real-
robot benchmark, with ten demonstrations per task and five demonstrated placement regions, TACIT achieves 66.7% success on ball placement and 73.3% on peg insertion, compared with 10.0% and 20.0% for input-matched 3D visuotactile fusion and 20.0% and 43.3% for
vision-only DP3. TACIT enters the 150 mm palm-to-object approach region within 12 seconds in all 30 trials per task; all remaining failures occur after arrival. Across three training seeds on real ball and simulated peg, TACIT outperforms input-matched fusion and an architecture-matched control without explicit
attention supervision, supporting the contribution of supervision beyond branch capacity. Pre-contact and contact-time supervision show no consistent ordering. These results demonstrate that measured tactile contact provides effective spatial supervision for approach behavior from few demonstrations within the evaluated workspace.
Read the full abstract ▾
All authors Yanhou Lai, Fucai Zhu, Ruiqiang Wang, Koichi Hashimoto
Machine Learning
On Emergent Capabilities and Model Merging
Luca Zhou and Emanuele Rodolà
Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does to emergent capabilities: behaviors an artifact carries that were never an explicit training target. Studying two independent testbeds (activation oracles and emergent-misaligned models) across three model families, we find that the answer is threefold. First, merging preserves an emergent capability that both parents carry: merging two misaligned checkpoints retains most of their broad misalignment across the whole mixing range. Second, merging cannot create an emergent capability that is superadditive in its parents: no weighted merge of two single-task oracles reaches the jointly-trained oracle's
auditing ability. Third, when only one parent carries the capability, merging dilutes it faster than the trained capability that accompanies it: the gap is significant in most settings. In short, emergent behaviors of an artifact do not compose the way its trained capability does.
Read the full abstract ▾
Cryptography and Security
Prefix Puncturable Signatures with Smaller Signing Key from HIBS
Masayuki Tezuka and Keisuke Tanaka
Puncturable signatures, proposed by Bellare et al. (EUROCRYPT 2016), allow a signing key to be punctured (updated) so that it loses the ability to sign particular messages while retaining the ability to sign all others. Halevi et al. (ASIACRYPT 2017) introduced prefix puncturable signatures, in which the signing key can be punctured with respect to a target prefix so that it cannot sign messages whose prefixes match the target prefix. So far, several generic constructions of prefix puncturable signature schemes have been proposed, including constructions based on identity-based signatures (IBS) (ESORICS 2022) and delegated constrained signatures (IEEE Trans. Inf. Forensics Secure. 2024). However, these constructions suffer from drawbacks in terms of key size. When the prefix space is the set of all l-bit strings, the former construction requires a signing key consisting of 2^{l} IBS signing keys. The latter construction, when instantiated with a
lattice-based delegated constrained signature scheme, yields a punctured signing key whose size grows quadratically with the number of puncturing operations Q^{Punc}. In this paper, we present a generic construction of prefix puncturable signatures from hierarchical identity-based signature (HIBS) schemes. When the prefix space is {0,1}^{l} and our construction is instantiated with the
lattice-based HIBS scheme HIBS^{GPV} by Ruckert (PQC 2010), our construction achieves a punctured signing key size bounded by O(lQ^{Punc}).
Read the full abstract ▾
Robotics
A Monolithic Force-Proprioception Soft Acutuator Enabled by Single-Material 3D printing
Nan Huang, Lele Liu, Junfeng Lu et al. (+3 more)
Pneumatic proprioceptive actuators integrate actuation and sensing for soft
robots that attract interest due to functional potential. Existing approaches often suffer from assembly errors or stress concentrations caused by heterogeneous materials. In this work, we propose the Monolithic Force-Proprioception Soft (MFPS) design and fabrication method that integrates an Asymmetric Origami Bending (AOB) chamber and a Force-Proprioception Soft (FPS) sensor with single material through one-step Fused Deposition Modeling (FDM) fabrication. Based on the resistance response to strain of conductive thermoplastic polyurethane (TPU), we design and analyze the structure of the FPS sensor, and conduct parametric analysis on the sensing characteristics. The FDM fabrication parameters of the MFPS actuator are analyzed, followed by actuator fabrication and characterization of the actuation and proprioception performance. Experimental results show that the MFPS actuator achieves a bending angle of 40{\deg}, an output force of 12.5 N, and a resistance change of 26.9% as the applied external force increased from 0 to 45 N. A two-finger force-proprioception gripper is developed based on the MFPS actuator. The grasping and force-proprioception capabilities are experimentally validated, proving that the MFPS design method provides a new approach for the development of self-sensing actuators.
Read the full abstract ▾
All authors Nan Huang, Lele Liu, Junfeng Lu, Yipan Zhu, Jiansheng Dai, Sicong Liu
Robotics
ScaleMPA: Rethinking Scalable RRT* Acceleration With a Grid-Native Representation
Zilong Wang, Yuzhou Chen, Xinyue He et al. (+2 more)
Real-time motion planning remains challenging in large and high-dimensional environments. Prior acceleration of RRT* follows tree-centric state organization, which reduces per-query cost but preserves superlinear end-to-end complexity and limits parallelism through structural dependencies. This paper presents ScaleMPA, a motion-planning accelerator that rethinks RRT* with a grid-native representation. By replacing hierarchical traversal with direct grid-based access, ScaleMPA reduces the planner critical path and exposes fine-grained parallelism. To make this reformulation practical under sparse high-dimensional planning, ScaleMPA further proposes a multi-resolution grid search engine and a hash-grid
memory system. Implemented in 28 nm CMOS, ScaleMPA achieves millisecond-level planning latency and delivers 4.7$\times$–44.4$\times$ speedup over state-of-the-art motion-planning accelerators.
Read the full abstract ▾
All authors Zilong Wang, Yuzhou Chen, Xinyue He, Chen Zhang, Guanghui He
Computer Vision
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
Xuezhi Xiang, Jiayao Liu, Heqi Xiang et al. (+3 more)
Accurate
monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised
monocular depth estimation methods generally suffer from the bottleneck of inefficient cross-scale information interaction and difficulty in balancing local and global spatial modeling. In this paper, we propose CMambaDepth, a self-supervised framework that achieves efficient multi-scale feature fusion and fine-grained contextual modeling via channel-wise selective state propagation. Specifically, Bidirectional Channel Mamba (Bi-CMamba) aligns encoder features across scales and enables bidirectional information exchange among ordered scale groups. Unidirectional Channel Mamba (Uni-CMamba) progressively aggregates decoder features and retains fine-grained scale groups through a group selection mechanism for subsequent fusion. Furthermore, a Hybrid
Attention Module (HAM) is introduced to combine large-kernel local context and Manhattan self-
attention for complementary spatial modeling. Experimental results demonstrate that our method achieves highly competitive performance. Specifically, our model achieves an AbsRel of 0.094 and an RMSE of 4.156 on KITTI, and an AbsRel of 0.140 on DDAD. In the zero-shot cross-
dataset generalization test on NYUv2, it attains an AbsRel of 0.232, outperforming the baseline RA-Depth by 7.2%.
Read the full abstract ▾
All authors Xuezhi Xiang, Jiayao Liu, Heqi Xiang, Yuqi Hu, Yiming Chen, Shanjun Zhang
Computer Vision
Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System
Bertil Braun and Felix Muehlenberend
Long-shot windsurfing
video combines small targets, large camera pans, prolonged overlaps, and rapidly changing backgrounds. The desired output is not a generic MOT trace but a separate, stable rider-relative
video for each surfer; one false identity merge can invalidate an otherwise useful result. We present an offline analysis system that detects surfers, forms conservative local tracklets, links them globally with camera-compensated motion and a foreground-masked sail-color descriptor, and uses two pose keypoints on the rig to drive a rider-relative virtual camera. The tracking stage is evaluated on 21 manually reconstructed development
videos containing 41,004 retained observations. On this fixed-observation protocol, the production system achieves 0.957 pairwise precision, 0.918 recall, and 0.937 F1, compared with 0.792 F1 for OC-SORT and 0.828 for BoT-SORT. Compared with OC-SORT, it reduces fragmentation excess from 845 to 42, but nine of its 95 output tracks mix rider identities and these errors affect seven of the 21
videos.
Read the full abstract ▾
Machine Learning
Lifted Bellman Linear Programming for Offline Reinforcement Learning
Hyukjun Yang, Jongchan Park, Narim Jeong et al. (+1 more)
Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target networks with exponential moving average (EMA) updates. Multi-step targets incorporate behavior-policy actions and therefore require off-policy correction. We instead impose in-sample Bellman optimality on the critic through inequality constraints. We formulate the Lifted Bellman Linear Program (LBLP), which lifts the linear programming characterization of Bellman optimality to the joint $(Q,V)$ space so that every constraint involves only state-action pairs in the
dataset. Its unique minimizer is the in-sample optimal pair, and constraints along $K$-step segments of
dataset trajectories leave this minimizer unchanged for any rollout policy and horizon. Under deterministic dynamics, this minimizer lies between the best
dataset return and the optimal value. Relaxing the constraints into hinge penalties recovers the same solution above a finite penalty coefficient in the tabular case. Approximate Lifted Bellman Unconstrained Minimization (ALBUM) implements this relaxation with neural networks and detaches the $K$-step rollout targets by stop gradient. Its objective contains no squared regression onto bootstrapped targets, so it can be trained without target networks or EMA updates. Under deterministic dynamics, the LBLP solution is a stationary point of the detached update under a coefficient condition independent of $\gamma$ and $K$, and the inequality constraints allow discounted returns along
dataset trajectories to serve as lower bounds without off-policy correction or action chunking. On OGBench, ALBUM uses a single critic with a Gaussian policy, matches the average performance of FQL, and is comparable to recent action-chunking methods, while using the fewest parameters and the least peak GPU
memory among all compared methods.
Read the full abstract ▾
All authors Hyukjun Yang, Jongchan Park, Narim Jeong, Donghwan Lee
Computer Vision
AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
Kirill Mazur, Nikita Karaev, Matthew Chang et al. (+2 more)
In this work, we present a method for shape reconstruction and tracking from
video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixel correspondences and then recover object motion from them, our method infers a structured 3D object model, including its geometry and kinematic structure, and uses this model to optimise object track estimates over time. In our optimisation loop, a
Vision-
Language Model (VLM)
agent iteratively refines shape or generalised pose through a render-and-compare loop, combining coarse visual
reasoning with numerical pose optimisation for precise state estimation. This structured formulation enables our method to track through large motion, articulation, and severe occlusion without relying on pixel-matching objectives. Quantitatively, on ARCTIC, our method substantially outperforms state-of-the-art 3D point-tracking baselines for articulated objects, and on HOT3D it outperforms all evaluated rigid-object tracking baselines.
Read the full abstract ▾
All authors Kirill Mazur, Nikita Karaev, Matthew Chang, Jitendra Malik, Nur Muhammad "Mahi” Shafiullah
Computer Vision
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
Guangchuan Lv, Dianxing Shi and Dingjie Fu
Visual
token pruning is a promising approach to reducing the inference cost of large
vision-
language models (LVLMs), yet aggressive
token reduction often causes substantial performance degradation. We identify three key factors behind this degradation: text-guided selection bias, information loss from discarded
tokens, and positional distortion caused by sequence compaction. Based on these observations, we propose VPRune, a training-free pre-LLM
pruning framework consisting of visual-only diversity selection, similarity-guided
token recycling, and position-preserving restoration. Experiments on FastVLM-1.5B across multiple
vision-
language benchmarks demonstrate that VPRune achieves a favorable accuracy–compression trade-off, with particularly pronounced advantages under aggressive compression. Furthermore, evaluations on edge-device show that VPRune effectively reduces end-to-end inference latency while maintaining superior task performance, demonstrating its practicality for resource-constrained LVLM deployment.
Read the full abstract ▾
Computer Vision
STA-TFM: Spatio-Temporal Aggregation Across Views TransForMer for Pose Estimation
Mena Kamel, Natalie Won, Amrut Sarangi et al. (+2 more)
Monocular 3D human pose estimation (HPE) remains challenging due to depth ambiguity, occlu- sions, and the need for temporal consistency. While multi-view methods provide superior accuracy over
monocular approaches, they often require complex setups. We introduce STA-TFM, a
transformer-based architecture that combines spatial and temporal information for multi-view pose estimation. The approach leverages DSTformer, a
monocular feature extractor, to capture long-range pose dependencies within each view. A fusion
transformer then aggregates information across views to produce coherent 3D estimates. To address training data scarcity, we use a data generation pipeline that transforms any existing 3D pose
dataset into multi-view setups with controllable parameters. Experiments on various
datasets demonstrate that STA-TFM outperforms existing camera-parameter-free multi-view methods. STA-TFM achieves 50.9% and 49.5% reductions in mean per joint position error (MPJPE) and mean per joint velocity error (MPJVE) on the DHP19
dataset. Furthermore, it achieves 6.7% and 7.7% respective reductions on HAA4D, and a 15.2% MPJPE reduction on TotalCapture. STA-TFM handles noisy and missing 2D inputs, supporting potential deployment in healthcare monitoring, athletic assessment, and immersive technologies. Code, training checkpoints, and data are available at https://zenodo.org/records/22832620.
Read the full abstract ▾
All authors Mena Kamel, Natalie Won, Amrut Sarangi, Sven Jager, Albert Pla Planas
Artificial Intelligence
Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards
Kalash Shah, Kunal Singh, Snehan J et al. (+1 more)
Deploying Large
Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic
reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to produce a diagnosis, and clinical healthcare
reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not exist. Recent
benchmarks such as HealthBench and MedXpertQA reveal persistent weaknesses in both areas, exposing failures in complex diagnostic scenarios and limitations in contextual, patient-centered dialogue. We introduce a sequential training framework that targets these facets using synthetic data and rubric-based reinforcement learning. First, we improve diagnostic
reasoning using MedBullets-derived questions with rule- and rubric-guided Reinforcement Learning (RL). We then shift to clinical
reasoning by generating 5.3k synthetic multi-turn scenarios, each paired with multi-dimensional rubrics to comprehensively assess the response. This approach yields over 10% improvement on MedXpertQA, and our 30B model achieves 50.1% accuracy on HealthBench-Hard, surpassing proprietary baselines including GPT-5 (thinking). Our results show that targeted synthetic
datasets and rubric-based training can systematically improve both diagnostic and interactive clinical
reasoning in medical LLMs.
Read the full abstract ▾
All authors Kalash Shah, Kunal Singh, Snehan J, Shreyas Singh