Computer Vision
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization
Junming Feng, Panwang Xia, Qiong Wu et al. (+8 more)
Satellite-ground localization estimates the planar position and yaw orientation of a ground camera within a geo-referenced satellite image. Most recent methods map ground and satellite features into a shared bird's-eye-view (BEV) space and establish spatial correspondences. However, insufficient depth constraints can assign one ground feature to different distances along a viewing direction, creating
geometric ambiguity in BEV feature placement. Similar appearances at different locations can also create descriptor matching ambiguity, while existing descriptor learning lacks explicit semantic supervision to distinguish them. We propose GeoSem-BEV, a geometry-semantic constrained BEV representation learning method. Radial depth supervision constrains distance assignment, and vertical height supervision constrains height aggregation. Shared explicit semantic supervision promotes consistent semantic predictions across views and helps distinguish locations with similar semantics. These constraints improve feature placement and descriptor discriminability, enhancing state-of-the-art BEV localization models. On VIGOR with unknown orientation, GeoSem-BEV reduces mean orientation error by 37.2% and 38.1% in the cross-area and same-area settings, respectively. The corresponding errors are reduced by 10.8% and 15.6% on DReSS-D. On KITTI-CVL, it reduces same-area mean orientation error by 26.8% under 10 degree orientation noise.
Read the full abstract ▾
All authors Junming Feng, Panwang Xia, Qiong Wu, Xudong Lu, Zeyu Jiao, Kun Lv, Zherong Wu, Yi Wan, Peifeng Ma, Li-Ta Hsu, Zhi Zheng
Robotics
LBDU-VIO: Learned Bias Dynamics and Uncertainty for Visual-Inertial Odometry with Unreliable Vision
Qizhi Guo, Junning Lyu, Defu Lin et al. (+1 more)
Visual-inertial odometry (VIO) for aerial
robots relies on high rate inertial measurement unit (IMU) propagation between visual updates. However, conventional multi state constraint Kalman filters (MSCKFs) use random walk bias assumptions and fixed noise parameters, which can limit robustness when visual information is unreliable. To address this problem, we propose LBDU-VIO, a learning-augmented MSCKF with learned continuous time bias dynamics and an IMU uncertainty model. A neural ordinary differential equation (ODE) models continuous time bias dynamics to propagate the filter's bias states, replacing their random walk model. The IMU uncertainty model predicts motion adaptive measurement noise covariances for covariance propagation. Both models are trained with pose supervision without direct labels. Experiments on real world EuRoC and TUM-VI
benchmarks show lower errors than representative visual-inertial baselines, including a 25.1% reduction in mean relative position error compared with S-MSCKF on EuRoC sequences with 10s visual outage.
Read the full abstract ▾
All authors Qizhi Guo, Junning Lyu, Defu Lin, Shaoming He
Machine Learning
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
Mohamed Amine Ketata, Maximilian Schambach and Stephan Günnemann
Generative models for tabular data are typically trained separately for each
dataset, limiting knowledge transfer and requiring the storage of many specialized models. In this paper, we introduce CDMD, a tabular
diffusion model trained jointly across heterogeneous
datasets with different schemas and variable numbers of numerical and categorical features. Unlike existing cross-
dataset tabular
diffusion models that operate in continuous representation spaces, CDMD defines
diffusion directly over the mixed-type feature space and is trained end-to-end. To accommodate heterogeneous categorical domains, we introduce a schema-restricted reverse-process parameterization for masked
diffusion models, in which the output space dynamically adapts to each feature's vocabulary. We then compose numerical and categorical feature-level
diffusion processes into a schema-dependent row-level process. A shared schema-aware
Transformer denoiser captures dependencies between features and parameterizes the reverse process across varying schemas. On seven real-world
datasets, a single jointly trained CDMD achieves the highest average generation quality among strong single-
dataset and cross-
dataset baselines, while using substantially fewer total parameters than the collection of separately trained models. Furthermore, pre-training on a corpus of 337
datasets improves generation on previously unseen
datasets under both limited target data and limited adaptation epochs. These results demonstrate the potential of direct mixed-type
diffusion for shared and transferable tabular data generation. Our code is available at https://github.com/ketatam/cdmd.
Read the full abstract ▾
Machine Learning
Prequential E-Values for Selected-GP Near-Optimality Certificates
Ami Tavory and Noa Cohen
When optimizing an expensive black-box function sequentially, as in hyperparameter optimization, we may want to stop once the best evaluated value is certified within $\varepsilon$ of the global optimum. Such a certificate needs two ingredients: a lower confidence bound for the selected value and an upper confidence envelope over the domain, typically supplied by a Gaussian process (GP). GP-UCB-style stopping rules are valid when the kernel and constants defining this envelope are fixed before the run, but the practical temptation is to tune the envelope from the same adaptive evaluations and then certify as if it had been fixed. We use prequential e-values to make this selection auditable: starting from a predeclared set of fully specified GP/RKHS envelopes, each candidate is tested by its own one-step-ahead e-process, contradicted candidates are deleted, and certification uses the largest upper bound among the survivors. With a valid selected-point lower bound and one declared candidate having valid latent coverage and noise calibration, the rule is anytime-valid. On a 512-seed noisy RBF stress sweep, it roughly halves false-certification risk at comparable power versus fit-then-certify. Relative to random fixed GP precommitment on smooth $d=3,4$ objectives, each additional false certificate is accompanied by 3.0 and 13.5 additional correct certificates, respectively.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Metachecks in Bivariate Bicycle Codes: Syndrome Distance, Measurement Faults, and Repair Limits
Mohammad Rowshan
Faulty syndrome measurements can corrupt an otherwise correct
quantum-error correction step. Bivariate bicycle (BB) codes contain dependent stabilizer checks, so every valid syndrome obeys additional parity constraints, or metachecks. We study how far this built-in redundancy can identify measurement faults and when the remaining ambiguity is unavoidable, while separately checking the code's logical structure. A logical decomposition is used as a preliminary safety check: it identifies a $k/2$-dimensional annihilator subspace and a $k/2$-dimensional colon quotient, and the minimum-weight logical need not be visible from the annihilator side alone. On the measurement side, translation
symmetry partitions syndrome locations into classes that carry identical metacheck information. This gives an exact characterization of the leading single-fault ambiguity, a bound on how many fault locations can be distinguished, and a family-level repair limit when the encoded dimension stays bounded while the block length grows. Under a static-data assumption, the same calculation gives the minimum number of checks that must be remeasured to remove every single-fault ambiguity. Exact finite-code calculations illustrate both regimes: all single measurement faults are distinguishable in a 72-
qubit BB code, whereas the 144-
qubit Gross code merges its 72 syndrome locations into 36 indistinguishable pairs. In a 108-
qubit example, one logical component first appears at weight 12 while the other contains a weight-10 logical. Sustained phenomenological experiments show that joint data–measurement decoding is more robust than a separated repair stage on the more ambiguous codes. The resulting tests apply to general two-block BB codes, including non-coprime periods and repeated-root cases.
Read the full abstract ▾
Computer Vision
Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation
Siyuan Liu, Kanghui Tian, Yue Duan et al. (+4 more)
On-policy
distillation (OPD) improves
reasoning by providing
token-level supervision from a teacher on a student's own trajectories. Existing methods primarily focus on enhancing this teacher-side guidance (e.g., by enriching teacher inputs and refining teacher feedback), yet we find that limited student perception is another critical bottleneck in
multimodal OPD. By providing oracle visual facts, the performance of OPD-trained students can still be substantially improved for both weak and strong teachers. To address this bottleneck, we propose S-OPD, a simple
multimodal on-policy
distillation framework that explicitly strengthens student perceptual learning through two objectives. Specifically, Teacher-calibrated Policy Contrast separates student policies under original and masked images with teacher-based
token-level gating, strengthening the student's reliance on visual evidence during
reasoning. Policy Agreement aligns student policies under original and noise-perturbed images, further improving perceptual robustness to visual noise. Notably, our method can be seamlessly plugged into existing OPD frameworks, requiring no additional data annotations, model parameters or inference operations. Extensive experiments on eight
benchmarks across student scales and
distillation paradigms demonstrate consistent performance improvements, with gains of up to 4.25 points on LogicVista. When combined with existing teacher-side supervision methods, our method can yield further gains. Code is available at https://github.com/Sirilaw/S-OPD.
Read the full abstract ▾
All authors Siyuan Liu, Kanghui Tian, Yue Duan, Yutao He, Shangdong Yang, Jian Zhang, Yinghuan Shi
Computation and Language
Yang Li, Gongle Xue, Yuheng Yuan et al. (+4 more)
On-policy self-
distillation (OPSD) has attracted growing interest as a promising approach to improve the
reasoning ability of
language models. Without external rewards nor a separate stronger teacher, the self-teacher with privileged information could provide dense signals on student's trajectories. However, its behavior in
language reasoning remains unclear, with reported outcomes ranging from modest gains to behavioral collapse. In this work, we diagnose OPSD for mathematical
reasoning across models spanning 0.6B–8B parameters. We conduct controlled experiments and
token-level analyses to fully delve into OPSD. We point out that teacher's signal is shaped by
reasoning-mode
alignment and the complete teacher prefix, rather than by privileged semantics alone. OPSD improves
reasoning only in narrow compatibility regimes. Otherwise, it produces ineffective length growth, stable degradation, or behavioral collapse.
Token-level analysis shows that teacher's signal is not stable and does not predict downstream performance. Based on these results, we argue that OPSD is a sensitive
algorithm rather than a generally reliable
reasoning-improvement post-training method.
Read the full abstract ▾
All authors Yang Li, Gongle Xue, Yuheng Yuan, Yijia Guo, Shizhe Zhang, Liwen Hu, Lei Ma
Cryptography and Security
SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models
Xinwei Zhang, Aoting Hu, Hangcheng Liu et al. (+3 more)
Activation steering offers an inference-time defense for
vision–
language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, protection on
benchmark inputs may not persist across alternative expressions of the same harmful request. We investigate this gap using fixed textual, visual, and joint reformulations designed to preserve the underlying intent, and find that these changes can bypass representative steering defenses. A complementary local analysis provides a sufficient condition under which a reformulation can cross a surrogate safety margin despite any admissible change in the local steering correction. We then introduce SteerProbe, an output-only black-box attack that learns to select effective reformulations for unseen requests from a shared calibration budget. Across three VLM backbones, two
benchmarks, and three steering defenses, SteerProbe increases Harmful Rate in all defended settings using 500 total calibration queries per endpoint and
benchmark, raising the average from 7.43% to 18.36%. These findings highlight that robustness on original
benchmark inputs is insufficient to characterize the safety of steering defenses and motivate reformulation robustness as an important evaluation dimension. They further motivate steering mechanisms that preserve safety across intent-preserving
multimodal variations while maintaining benign utility.
Read the full abstract ▾
All authors Xinwei Zhang, Aoting Hu, Hangcheng Liu, Shuchao Pang, Qingqing Ye, Haibo Hu
Computer Vision
GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking
Shiyang Liu, Weiquan Lin, Luping Xiao et al. (+4 more)
Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB
video without object-specific CAD models, posed reference images, or pose annotations.
Geometric foundation models provide complementary object-centric and scene-centric cues, yet SAM3D CAD is indexed by an arbitrary object-local surface parameterization, whereas reconstructed evidence is expressed in a sequence-specific world frame with partial surface coverage. To exploit this complementarity, we formulate tracking as generation-reconstruction correspondence and introduce GRC-Pose, a correspondence-based framework that combines learned correspondence prediction with robust pose estimation. Concretely, GeoCorr-Matcher estimates weighted object-scene correspondences and per-match uncertainty for each pose candidate. FGH-Solver integrates these matches through multiple robust
geometric estimators and sequence-level posterior inference, while a posterior-gated
memory retains only inlier-supported observations through occlusion and viewpoint change. Extensive evaluation shows that with SAM3D CAD, GRC-Pose achieves state-of-the-art Average Recall and motion retention on HOT3D, improving the latter by 58% over prior art. On classical
benchmarks including YCBInEOAT and LINEMOD, it remains highly competitive.
Read the full abstract ▾
All authors Shiyang Liu, Weiquan Lin, Luping Xiao, Jiadong Tang, Yi Yang, Yu Gao, Xingyu Chen
Computer Vision
Beyond Local Linearity: Scale-Resolved Geometry of Learned Image Encoders
Jakub Szymkowiak, Wojtek Pałubicki and Kamil Adamczewski
Understanding how learned representations respond to finite input changes is important for characterizing their sensitivity, invariances, and robustness. Yet existing
geometric analyses are predominantly local and describe only infinitesimal perturbations. We introduce a scale-resolved statistic that compares an encoder's measured feature displacement with its local linear prediction as the perturbation magnitude increases. Across diverse image encoders, we discover a characteristic plateau-rise-peak-decay profile, which we call the bump. The bump is absent at initialization, emerges early during standard training, and does not form under randomized labels or random-noise inputs. Its shape also varies with the training distribution and robustness objective. These results establish departures from local geometry as a signature of how encoder representations are shaped by learning.
Read the full abstract ▾
Machine Learning
The Row Normalization Puzzle in Muon
Jiayu Zhang and Tianyi Lin
This paper examines how row-wise renormalization affects
Muon, focusing on the gap between NorMuon's worst-case guarantees and its practical performance (Li et al.). Despite its growing adoption and promising performance in large
language model (LLM) pretraining, NorMuon's worst-case guarantees remain poorly understood. One fundamental question is: Does row normalization yield provable convergence gains, potentially through its interaction with approximate polar computation and exponential moving-average momentum? Our results show that row normalization introduces a dimension-dependent factor in the worst-case iteration complexity under the operator-norm geometry, which persists even with exact polar computation and any fixed momentum parameters. Indeed, we establish an
algorithm-dependent lower bound and a matching upper bound in deterministic settings, and extend our upper bound analysis to
stochastic settings. Both upper-bound analyses allow approximate polar computation. Experiments show that NorMuon is slower than
Muon on synthetic problems inspired by our worst-case construction, yet outperforms
Muon in LLM pretraining. These findings sharpen the puzzle of why row normalization helps in practice and complement the recent findings of Dewulf et al.
Read the full abstract ▾
Computer Vision
CamAgent: An LLM-Agent Framework for Multi-Species Camera-Trap Workflows
Yutong Deng, Qi Song, Xi Guo et al. (+3 more)
Camera traps accumulated vast, multidimensional data for wildlife monitoring, yet translating raw media archives into meaningful ecological insights remains highly fragmented. Current research workflows require laboriously stitching together disparate analysis tools and scripts, creating steep programming hurdles and complicating end-to-end spatiotemporal analyses. To overcome this fragmentation, we present CamAgent, an autonomous Large
Language Model (LLM)
agent framework that integrates camera-trap analytical workflows into a unified intelligent ecosystem. CamAgent interprets natural-
language ecological intent, schedules computational routing, and executes specialized tools spanning computer-
vision perception (e.g., SpeciesNet), CamtrapDP-compatible data management, detection-corrected occupancy modeling, temporal activity analysis, and species co-occurrence networks. The framework automates multi-stage analytical pipelines while maintaining essential data-quality controls and analytical conventions. Consequently, CamAgent significantly reduces manual programming overhead for conservationists, establishing a transparent, scalable, and fully integrated paradigm for camera-trap ecology. Our project is available at https://anonymous.4open.science/r/artifact72c6f4.
Read the full abstract ▾
All authors Yutong Deng, Qi Song, Xi Guo, Tianming Wang, Lei Bao, Jianping Ge
Computation and Language
Bongard: Training Machine Intuition
Li Ding, Haidi Jin and Chen Ji
Human intelligence relies heavily on learned intuition: recognising patterns and judging situations without explicitly unfolding every intermediate step. We introduce Bongard, an open-weight System One model that treats machine intuition as an independent capability to design and train. A T5Gemma 2 4B-4B encoder-decoder separates reading the evidence from making judgments. The encoder reads the state bidirectionally together with the question instructions, and separate decoder branches share this encoding, so many judgments about the same situation require only one reading of the state. A trained head returns probabilities over the supplied candidates without generating text. Training proceeds in three stages, from supervised judgments to semantic relationships to action outcomes, and each stage updates all 7.09 billion trainable parameters on one Blackwell GPU. Joint-
embedding post-training raises accuracy on held-out rephrasings from 75.7% to 85.9%. A sandbox stage then learns outcome distributions from action rollouts and exact oracles, raising accuracy on a frozen sandbox panel from 50.6% to 64.8%. On DecisionBench, the final model reaches 78.05% accuracy over 23,900 decisions and ranks fourth of 61 systems in the public comparison. On one RTX PRO 6000, its median latency is 36 ms for short requests, and 32 questions about one state take 221 ms. Bongard demonstrates that machine intuition can be systematically trained via representation learning and outcome feedback, providing an open, efficient alternative for high-throughput decision workloads.
Read the full abstract ▾
Machine Learning
T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning
Liuxian Ma, Jiale Dai, Jiaqi Li et al. (+1 more)
Parameter-efficient reinforcement learning aims to improve
reasoning with a compact trainable interface to a pretrained model. We introduce the Thalamic Router (T-Router), which concentrates adaptation on the reuse of completed computations. A compressed, addressable bank preserves block changes; a depth-recurrent controller conditions their selection and relative-scale writeback. This coupling gives thalamic context-dependent routing a concrete computational form: learn which earlier contributions a receiving layer uses, and with what influence. Correctness rewards train the interface while preserving backbone parameters and layer order. On an 8.95B-parameter backbone, T-Router allocates 41.73M parameters (0.466% of the backbone) and achieves 83.64 +/- 1.16 MathAvg after GSM8K RL, compared with 73.79 +/- 1.83 for full-parameter GRPO across three evaluation rounds. At a comparable parameter budget and with matched retries, it exceeds LoRA's 77.28 +/- 1.95 MathAvg, improving all three task families and raising mean AIME accuracy from 48.33 to 60.56. Capacity-controlled comparisons favor addressable block changes and recurrent context; separate search training extends the interface to tool-mediated
reasoning. These results establish controlled computation reuse as an effective route to parameter-efficient
reasoning reinforcement learning.
Read the full abstract ▾
All authors Liuxian Ma, Jiale Dai, Jiaqi Li, Lu Mi
Artificial Intelligence
MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models
Yan Zhang, Chuming Wei, Ruien Li et al. (+3 more)
Large
Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and bias, still remains a challenge. Current efforts mainly focus on detecting and filtering inputs and outputs of the trained models, rather than studying the intrinsic architecture of the models in real-time. To tackle this challenge, we analyze the LLMs training process and discover two critical issues: 1) Most of the existing methods are predominantly static in their approach to detection and filtering, achieving only localized optimizations without systematically enhancing the compliance of LLMs. 2) Another issue with existing approaches is the lack of real-time risk detection and mitigation across the full training process, which leads to limited flexibility. Motivated by these, we propose MASCRDM (Multi-
Agent System for Compliance Risk Detection and Mitigation) during the LLM training process. Firstly, we develop a set of compliance rules based on existing Artificial Intelligence (AI) laws and a compliance-specific LLM with the instruction of compliance law experts. Then, we deconstruct LLMs into several components and identify key nodes based on the compliance knowledge graph. During LLMs training, we implement our multiple
agents in the whole process, giving compliance risk alerts and suggestions for LLM developers. Experiments on discrimination and bias
benchmark demonstrate that our multi-
agent system can effectively improve the compliance while maintaining reasonable semantic performance. The results indicate that our method provides an executable path for mitigating compliance risk from within the LLMs systematically.
Read the full abstract ▾
All authors Yan Zhang, Chuming Wei, Ruien Li, Yaoyao Peng, Wusheng Zhang, Guangwen Yang
Artificial Intelligence
Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines
Qinchuan Cheng
Conservative bandits must improve an incumbent policy without exhausting a prescribed performance budget. When the incumbent is uncertain, separately bounding candidate and baseline rewards can charge twice for shared estimation error. We develop Reserve-C4B around the baseline-relative contrast itself. A shared confidence set yields an exact expression for this avoidable penalty and a tighter admissibility test at every fixed history. A reserve ledger separates statistical evidence from permitted performance deficit; a prefix-refresh extension recertifies accumulated decisions under the current confidence set without discarding previously certified credit. For linear rewards, self-normalized confidence sets provide simultaneous validity over time and adaptively generated candidates, and the resulting policy satisfies a conditional-mean performance constraint with high probability. Reproducible experiments isolate certificate coupling, prefix refresh, and historical information, showing large reductions in baseline fallback while exposing the limitations of frozen certificates.
Read the full abstract ▾
Robotics
Occlusion-Aware, Quasi-Static, Stability-Oriented Trajectory Planning on Uneven Terrain
Amith Manoharan, Chinmay Mundane, Aayush Bahukhandi et al. (+3 more)
Autonomous
navigation in unstructured off-road environments requires
reasoning about both vehicle–terrain interaction and environmental unknowns. We propose a model-based framework for generating quasi-static, stability-oriented reference trajectories for rigid, non-articulated four-wheeled vehicles on highly uneven terrain. Our work makes three primary contributions. First, we model blind spots caused by terrain occlusion as coverage-induced epistemic uncertainty in a fixed-feature
Fourier terrain representation, quantified through a regularized inverse-Hessian estimate. Second, we propagate this uncertainty through the Nonlinear Least-Squares (NLS) pose/contact model using implicit differentiation and incorporate the resulting pose, contact-point, and per-wheel surface-normal uncertainty terms into trajectory optimization based on the Cross-
Entropy Method (CEM). Third, we introduce a Flow Matching model that warm-starts terrain fitting, and we evaluate its fitting-accuracy–latency trade-off while retaining model-based refinement. Across six synthetic terrains with 30 matched start–goal pairs per terrain, the complete framework produced an observed failure rate of 18.9%, compared with 46.1% and 41.7% for two representative baselines and 34.4% for an ablation that removed the propagated-uncertainty scoring. Hardware evaluations span six distinct outdoor environments, with two representative executions presented in the paper and four additional executions included in the supplementary
video. The evaluation also reports the accuracy–latency trade-off for the Flow Matching warm start.
Read the full abstract ▾
All authors Amith Manoharan, Chinmay Mundane, Aayush Bahukhandi, K. Madhava Krishna, Karel Zimmermann, Arun Kumar Singh
Discrete Mathematics · Cross-listed from math.CO
On Eternal Connected Vertex Cover
Rajat Adak and Saraswati Girish Nanoti
For a connected graph $G$ with at least one edge, the eternal connected vertex cover number $ecvc(G)$ is the minimum number of guards that can maintain a connected vertex cover after every response to an arbitrary sequence of edge attacks. Denote the minimum size of a connected vertex cover by $cvc(G)$. It is known that $cvc(G)\leq ecvc(G)\leq cvc(G)+1$. A necessary condition for $ecvc(G)=cvc(G)$ is that every vertex belongs to some minimum connected vertex cover. We show that this condition is not sufficient: there exists a $32$-vertex graph $G$ that has $cvc(G)=19$ and $ecvc(G)=20$, although every vertex of $G$ belongs to some minimum connected vertex cover. For connected graphs with minimum degree at least two, we establish the sharp bound $cvc(G)\geq 2|V(G)|-|E(G)|-1$ and $\mathcal F$ denotes the class attaining equality. We prove that $G\in\mathcal F$ if and only if the vertices of degree at least three induce a forest. Within $\mathcal F$, the conditions $ecvc(G)=cvc(G)$, membership of every vertex in some minimum connected vertex cover, and the presence of at least two degree-two vertices on every cycle are equivalent. As applications, we obtain $ecvc(G)=cvc(G)$ for full subdivisions of connected graphs of minimum degree at least two and for minimally $2$-connected graphs. In both the families, every minimum connected vertex cover is an eternally winning configuration. This is not true in general for graphs outside $\mathcal{F}$, we show one example of such a graph.
Read the full abstract ▾
Computation and Language
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Meijia Chen, Hao Li, Zheng Lu et al. (+12 more)
Self-evolving search
agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward improves without a matching gain in external correctness. A post-hoc audit against source evidence shows co-cheating growing more severe over successive rounds of self-
evolution, with pseudo-label correctness stagnating or declining even as the in-loop training signal improves. The most direct mitigation is to verify proposals before training: we introduce multi-sample verification (MSV), which queries the same model three times with the source and three times without it to decide task admission and replace unreliable pseudo-labels. MSV partially reduces false agreement but leaves substantial residual co-cheating and costs six extra labeler generations per candidate. These limitations motivate CrossFit, our main method: it partitions the proposer's source documents into groups A and B; questions generated from A are scored by an auxiliary solver trained only on B, and vice versa. The cross-fitted agreement determines proposer reward, so a same-source pseudo-label cannot be reproduced through the feedback solver, while the original solver's update rule is unchanged. Rerunning the loop with Qwen3.5-4B and Qwen3.5-9B, MSV reduces false-agreement mass from 6.1% to 5.7% and from 8.8% to 7.2%, whereas CrossFit reduces it to 3.0% and 3.7%. Replaying identical proposals with source-excluded feedback further reduces false agreement to 0.4% and 0.1%, isolating feedback ancestry from curriculum changes. Across seven downstream search
benchmarks, CrossFit improves average performance over standard coupled self-
evolution by 8.8 and 8.4 points and over Search-R1 by 8.7 and 7.8 points at 4B and 9B.
Read the full abstract ▾
All authors Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin, Junbai Tian, Yichen Liu, Zijun Tian, Yufan Zou, Shuhan Sun, Hanxin Chen, Zeyu Zhang, Weizhi Du, Yueting Li, Tianyu Shi, Alaa Khamis
Artificial Intelligence
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Yongjiang Liu, Jie Zhang, Haoyue Zhang et al. (+3 more)
Equipping VLM
agents with world modeling capabilities has shown strong potential for complex
reasoning and long-horizon planning, while reducing the dependence of policy learning on costly real-world interactions. Existing methods mainly rely on prospective simulation to predict the consequences of candidate actions. However, this forward-only paradigm focuses on what will happen next and provides limited constraints for verifying whether an action is causally consistent with the observed state transition, which can lead to plausible-looking but physically incoherent behaviors. In this paper, we challenge the view of world modeling as only prospective prediction and introduce Retrospective World Modeling, a new
agent learning paradigm that enables
agents to reason backward by estimating the retrospective attribution distribution $P(\hat{a}{t}|s_t, s{t+1})$ for the action that most likely caused a given transition. Based on this capability, we formulate the Self-Consistency Reward (SCR), an intrinsic signal that measures the probabilistic consistency between the policy action and the retrospective explanation. Integrating SCR into reinforcement learning provides dense transition-level feedback and steers
agents toward behaviors that are both task-effective and physically grounded. Extensive experiments across diverse agentic tasks show that our method substantially improves policy robustness and generalization over prospective-only world modeling baselines.
Read the full abstract ▾
All authors Yongjiang Liu, Jie Zhang, Haoyue Zhang, Jingcai Guo, Deze Zeng, Song Guo
Machine Learning
A Generalisation Signal Need Not Be a Model-Selection Signal
Aditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar et al. (+5 more)
Model selection in computational biology often relies on validation data drawn from the training regime, even when deployment lies outside it. When validation no longer preserves which model is best, a natural alternative is to rank candidates using properties of the trained network itself. We test this idea using a novel, forward-only proxy motivated by the norm of the Hessian, alongside common Hessian measures, across molecular property,
protein fitness, and drug-response tasks. Contrary to our hypothesis, geometry does not become more useful as validation Spearman correlation deteriorates: augmenting validation helps some shifts but significantly harms others. More surprisingly, the proxy still correlates with generalisation gap on most tasks even when Hessian trace and top-
eigenvalue relationships are weak or reversed, yet this signal does not reliably identify the deployment-best model. A
curvature bound need not preserve cross-model rankings, and low
geometric scores can even favour collapsed predictors. Thus, a generalisation signal need not be a model-selection signal.
Read the full abstract ▾
All authors Aditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar, Vrishti Godhwani, Rahul Yedida, Aditya Challa, Danda Sravan, Snehanshu Saha
Robotics
DiFF: Doppler-informed Flow Matching for Human Motion Flow
Kai Wang and Mingle Zhao
Perceiving human motion via
privacy-preserving 4D millimeter-wave (mmWave) radar is critical for next-generation human-
robot interaction (HRI), where point cloud scene flow serves as a foundational motion representation. Yet the extreme sparsity and noise of 4D radar point clouds make non-rigid motion flow estimation severely ill-posed–a challenge that existing rigid-centric methods and prior works fail to adequately address, largely because they neglect the rich Doppler velocity cues inherent in 4D radar. We propose DiFF, a generative framework that marries Doppler-informed motion priors with a Kolmogorov-Arnold Network (KAN)-based conditional flow matching model. At its core, a KAN-
attention mechanism enables expressive feature extraction, while a prior-guided generative process harnesses Doppler cues to regularize the ill-posed solution space. Extensive experiments show that DiFF achieves state-of-the-art (SOTA) performance across diverse real-world
datasets, reducing 3D endpoint error to the millimeter scale on the mmBody
benchmark.
Read the full abstract ▾
Game Theory
Mechanism Design for Bridge Location with Optional Preferences
Xiaoshuang Geng, Wenjing Liu, Genjie Qin et al. (+1 more)
We study the bridge location problem with optional preferences, where two separated regions each contain one prelocated facility. Each
agent has a private location and a private preference specifying a nonempty subset of the two facilities in which she is interested. Her individual cost is measured by one of three natural variants: the maximum, the sum, or the minimum of her distances to the facilities in which she is interested. The social planner must design deterministic strategyproof mechanisms that elicit truthful reports, choose the location of a connecting bridge, and approximately minimize either the social cost or the maximum cost. Our main results are as follows. For the social cost objective, we design optimal mechanisms for the max-variant and sum-variant costs, and provide a 3-approximation mechanism for the min-variant cost, and establish a lower bound of 2 for the min-variant. For the maximum cost objective, we give 5/3-approximation mechanisms for the max-variant and sum-variant costs, and a 3-approximation mechanism for the min-variant cost; we also prove a common lower bound of 5/3 that applies to all three cost variants under the maximum cost objective.
Read the full abstract ▾
All authors Xiaoshuang Geng, Wenjing Liu, Genjie Qin, Qizhi Fang
Computer Vision
DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
Zeqi Xiao, Qingle Liu, Kaiwen Zhang et al. (+3 more)
Autoregressive
video diffusion supports streaming generation and interactive control, but its KV cache grows continuously with the generated history. Existing compression strategies either discard history using fixed windows or select
tokens through local
attention and similarity signals, which do not directly measure whether the current chunk contributes information beyond the retained context. We introduce DeCoPrune, a training-free method that treats cache compression as a denoising-consistency problem. We find empirically that denoising difficulty provides a useful proxy for a
token's value in long-term retention:
tokens with larger step-to-final discrepancies tend to carry visual evidence that is less predictable from the retained context. DeCoPrune measures each current-chunk
token's denoising difficulty using the discrepancy between its intermediate clean prediction and final denoised value, retaining high-discrepancy
tokens in the long-term cache while
pruning those with low discrepancy. To evaluate information retention, we introduce CMBench, comprising 58 approximately one-minute generated or real-world context episodes and 116 Reappear or Revisit continuation tasks that require recalling specific previously observed objects or scenes. Experiments with LingBot World v2 show that DeCoPrune preserves near-FullKV long-range recall while
pruning over 85% of historical KV
tokens and accelerating continuation generation by over $4\times$, substantially outperforming the evaluated compression baselines at comparable budgets. These results indicate that denoising consistency can serve as a model-intrinsic signal for retaining long-range information while reducing autoregressive inference cost. Our project homepage is https://decoprune.github.io. The code is available at https://github.com/DeCoPrune/CMBench, and the
benchmark at https://huggingface.co/
datasets/Aoraku/CMBench.
Read the full abstract ▾
All authors Zeqi Xiao, Qingle Liu, Kaiwen Zhang, Yifan Zhou, Zihan Ding, Xingang Pan
Machine Learning
Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation
Kihyun Yu, Seoungbin Bae and Dabeen Lee
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this setting either require computationally inefficient
algorithms or have suboptimal dependence on the number of interactions $T$. We propose, to the best of our knowledge, the first computationally efficient
algorithm that achieves $\widetilde{\mathcal{O}}(\sqrt{T})$ regret and cumulative constraint violation with high probability in the tabular setting. The $\sqrt{T}$ dependence is optimal up to logarithmic factors. Our approach incorporates cumulative constraint violation into the state and defines a reshaped reward through differences of a Huber potential. The added state determines the penalty on further violations while the reward function remains fixed on the augmented state space. Since the added state has known deterministic dynamics, only the original transition kernel needs to be estimated. The bounded slope of the Huber potential keeps the per-step reward bounded, and the potential differences
telescope to relate the reshaped return to the original cumulative reward and the terminal potential. These properties allow us to apply finite-horizon approximation and optimistic value iteration with clipping, as used in unconstrained average-reward MDPs, without worsening the regret rate in $T$.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models
Shokichi Takakura, Akifumi Wachi, Rei Higuchi et al. (+2 more)
Inference-time
alignment of flow and
diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's $h$-transform provides an elegant solution to this problem, and most existing methods are based on this principle. However, in practice, estimating the optimal guidance derived from Doob's $h$-transform at inference time is challenging. To deal with this issue, we regard inference-time
alignment as a sequential optimization problem in the space of probability measures and propose a novel framework called *Steepest Guidance*, based on the principle of maximizing local improvement in the objective. We provide a theoretical analysis of the proposed method and demonstrate its effectiveness through extensive experiments.
Read the full abstract ▾
All authors Shokichi Takakura, Akifumi Wachi, Rei Higuchi, Kohei Miyaguchi, Taiji Suzuki
Machine Learning · Cross-listed from physics.chem-ph
A strategic roadmap for an atomistic machine-learning ecosystem
Jörg Behler, Michele Ceriotti, Cecilia Clementi et al. (+47 more)
Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of matter is particularly widespread and impactful. This success is due largely to the existence of a well-developed and established physics-based modeling framework, ranging from first-principles electronic-structure calculations to molecular dynamics and statistical sampling, into which ML was integrated naturally to reshape long-standing trade-offs between accuracy, efficiency, and scale. Nevertheless, this integration raises both conceptual and practical challenges, from choosing between data-centric and physics-based modeling approaches to adapting established software stacks to modern hardware accelerators and ML libraries. As the field evolves rapidly, fueled in part by widespread enthusiasm but also by tangible impact, it seems appropriate to take a moment to consider the current state of the art and open challenges, and reflect on what can be done to better coordinate efforts across the community. With this goal in mind, several members of this community met in Lausanne in January 2026 at CECAM to discuss
algorithms, models, software and hardware infrastructure, and the most promising scientific applications that have become possible thanks to the use of artificial intelligence in atomic-scale simulations. This strategic roadmap paper summarizes the outcomes of these discussions, suggesting some long-term goals, and some concrete actions, to establish a healthy, sustainable and impactful atomistic ML ecosystem.
Read the full abstract ▾
All authors Jörg Behler, Michele Ceriotti, Cecilia Clementi, Gábor Csányi, Alin-Marin Elena, Aditi Krishnapriyan, Joseph W. Abbott, Fabio Affinito, Albert P. Bartók, Ilyes Batatia, Filippo Bigi, Florian N. Brünig, Yannick Calvino Alonso, Giuseppe Carleo, Aurélie Champagne, Stefan Chmiela, Marc L. Descoteaux, Ralf Drautz, Alexandra Farcas, Meng Gao, Rohit Goswami, Michael F. Herbst, Christian Holm, James R. Kermode, Alexander L. M. Knoll, Tobias Kreiman, Marcel F. Langer, Hoang-Thien Luu, Yury Lysogorskiy, Mihai-Cosmin Marinica, Rocco Meli, Klaus-Robert Müller, Frank Noé, Mohamadhosein Nosratjoo, Simon Olsson, Christoph Ortner, Aldo S. Pasos-Trejo, Anyang Peng, Eric Qu, Andrea Rizzi, Mariana Rossi, Bassem Sboui, Gregor N. C. Simm, Alexandre Tkatchenko, Jacopo Venturin, O. Anatole von Lilienfeld, William C. Witt, Brandon M. Wood, Tigany Zarrouk, Fabian Zills
Computer Vision
UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting
Zhihao Guo, Peng Wang, Zidong Chen et al. (+7 more)
Sparse-view 3D Gaussian Splatting is prone to overfitting because limited observations leave many Gaussian primitives weakly constrained, yet their contributions are still accumulated through alpha blending. Without uncertainty estimation, the renderer cannot distinguish unreliable primitives from well-constrained ones, allowing their erroneous contributions to corrupt novel-view synthesis. We introduce UGOD, an uncertainty-guided framework that estimates a view-dependent uncertainty score for each Gaussian and uses it to regulate its rendering contribution. A lightweight uncertainty head conditioned on Gaussian attributes and viewing direction predicts this score, which then drives a differentiable opacity-modulation mechanism that attenuates high-uncertainty primitives before compositing. During training, a detached soft-dropout branch applies an uncertainty-controlled continuous keep mask to discourage the model from relying on poorly constrained Gaussians and thereby reduce overfitting. Crucially, detaching the uncertainty score prevents gradients from this
stochastic regulariser from biasing or collapsing the uncertainty prediction. Experiments on Mip-NeRF~360 and LLFF show that UGOD improves sparse-view novel-view synthesis while producing more compact Gaussian representations than the compared methods. These results demonstrate that Gaussian uncertainty provides an effective rendering-time control for sparse-view reconstruction.
Read the full abstract ▾
All authors Zhihao Guo, Peng Wang, Zidong Chen, Xiangyu Kong, Yan Lyu, Guanyu Gao, Chenghao Qian, Ziyang Wang, Xinqi Fan, Liangxiu Han
Sound
SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS
Longyu Lu, Zongwei Du, Mengtao Xing et al. (+4 more)
Long-form live-streaming TTS requires context-dependent prosody and paragraph-level coherence. However, many existing instruction-based TTS systems use global or uniform conditions, providing limited explicit control over clause-level relative prosodic changes. We introduce Speaker-Relative Inline Prosody Control, where each Pitch, Energy, or Speed instruction targets a clause relative to the preceding clause from the same speaker, while Pause uses an absolute duration interval. In codec-based TTS, Speed and Pause affect sequence length, whereas Pitch and Energy rely on residual codebooks. By analyzing Qwen3-TTS RVQ codebooks, we find that Energy concentrates in early residual codebooks, whereas Pitch accumulates across a deeper prefix. We therefore propose Scope- and Codebook-Aware Instruction Conditioning (SCIC), combining a Temporal Instruction Router for frame-level tag activation with Tag-Specific Codebook Weighting over residual codebooks. SCIC improves speaker-relative Pitch and Energy control over standard instruction fine-tuning using text-
token tags. We further apply multi-reward GDPO post-training to jointly optimize control and quality, improving control accuracy while preserving CER and speaker similarity. In long-form synthesis, SCIC produces a more distinct paragraph-level expressive hierarchy than speaker-adapted SFT without instructions. Audio demos are available at: https://taoliveaigc.github.io/SCIC/
Read the full abstract ▾
All authors Longyu Lu, Zongwei Du, Mengtao Xing, Zhuoqun Liu, Zifan Guan, Meiguang Jin, Junfeng Ma
Software Engineering
Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail
Gou Tan, Pengfei Chen, Zhensu Sun et al. (+9 more)
Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate such healing code, but it is evaluated only on small competition programs, and executing LLM-generated code inside a live process raises safety concerns that remain unaddressed. In this paper, we take LLM-based runtime healing toward practical use in real-world repositories. We first build HealBench, a
benchmark of 265 runtime errors from 18 real-world repositories, each paired with a reference execution on the patched version. HealBench also provides a unified framework that lets LLM
agents heal with cross-file context and live runtime state. We then design HealGuard, which requires healing code to be written in HealCore, an analyzable subset of Python, and uses static and dynamic taint analysis to check whether state changed by healing reaches operations protected by developers. We evaluate a dedicated healing method and three general coding
agents with three backbone LLMs. The best setting resumes execution in 38.11% of instances and passes the target test in 28.68%, showing that existing
agents can already heal a meaningful share of real repository-level crashes. However, among executions that pass, HealGuard flags 17.4% whose healing-changed state may reach a protected operation. On 684 controlled cases, HealGuard detects all unsafe cases, at the cost of a 68.42% false positive rate.
Read the full abstract ▾
All authors Gou Tan, Pengfei Chen, Zhensu Sun, Jieke Shi, Junkai Chen, Ting Zhang, Weifeng Sun, Junda He, Shuai Liang, Chuanfu Zhang, Lwin Khin Shar, David Lo