Multiagent Systems
FlowMAS: Learning Multi-Agent Workflow Topology via Information-guided Generative Flow Network
Haitao Wang, Chenjing Liang, Haipeng Zhang et al. (+6 more)
Automated multi-
agent systems offer clear advantages over manually designed ones in scalability and adaptability, but existing workflow
topology methods still face important limitations. Search-based methods are often computationally expensive, textual-gradient-based methods rely on coarse-grained feedback, and existing generation-based methods are not well suited to discrete workflow
topologies with complex dependencies. To address these limitations, we propose FlowMAS, a multi-
agent workflow
topology method based on Generative Flow Networks (GFlowNets). FlowMAS models workflow generation as reward-guided flow over the
topology space and introduces three components: a GFlowNet-based
topology generation backbone, a curiosity-driven module for structure-aware exploration, and an information-guided optimization module for evaluating intermediate
topologies. Concretely, the curiosity-driven module encourages exploration of structurally novel workflows, while the information-guided module measures both the information contribution and the communication efficiency of different operators to favor more informative and effective collaboration patterns. Experiments on six
benchmark datasets with three LLM backbones show that FlowMAS consistently outperforms multiple baselines.
Read the full abstract ▾
All authors Haitao Wang, Chenjing Liang, Haipeng Zhang, Jiawei Hu, Sicheng Wang, Songzhu Mei, Chenglu Wen, Siqi Shen, Cheng Wang
Robotics
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts
Tianhang Pan, Xuanhao Wang, Yiwen Pang et al. (+4 more)
VLAs combine pretrained
vision-
language representations with action generation to enable
language-guided control across diverse tasks, becoming a mainstream paradigm in
embodied intelligence. However, multiple studies have reported VLA's substantial declines in task success under camera shifts, revealing a key vulnerability that limits reliable deployment. To address this vulnerability, existing methods collect paired observations of the same scene from different viewpoints to fine-tune the VLA or train visual adaptation modules. Unfortunately, they require additional data collection and VLA training costs. In this paper, we first identify cross-view coordination breakdown under external camera shifts: the
robot may rely too heavily on wrist-view cues and consequently execute subtasks in the wrong order when losing global view. Motivated by this, we propose CoRe-VLA, a plug-and-play framework requiring neither additional multi-view data collection nor VLA fine-tuning, which can incorporate with exsiting VLAs. It reconstructs a scene point cloud and renders the observation from the VLA's training viewpoint to restore cross-view coordination. In CoRe-VLA, Render-to-Camera (R2C) Restoration reduces rendering-induced visual degradation, while Execution-Trajectory-Conditioned
Alignment (ETCA) reduces
robot idle time and mitigates motion conflicts during asynchronous execution. Experiments on 5 real-
robot tasks, LIBERO-100 and LIBERO-Plus demonstrate CoRe-VLA substantially improves task success across mainstream VLAs under camera shifts. For example, CoRe-VLA raises PI0.5's success rate from 13.3% to 83.3% at a 1.6m camera shift in real-
robot environment.
Read the full abstract ▾
All authors Tianhang Pan, Xuanhao Wang, Yiwen Pang, Bo Zhou, Jun Yang, Min-Ling Zhang, Shimin Di
Machine Learning
Multimodal Detection of Higher-Order Behavioral Constructs: Self-Compassion in Structured Reflective Interaction
Siddhant Jain and Dimitra Tsovaltzi
Many of the qualities that matter most in how people learn and grow, how someone regulates their
emotions, reflects on a setback, or stays aware of others during a difficult conversation, are not directly observable. They have to be inferred from how someone speaks, moves, and sounds over time, and they resist the kind of clean labeling that most machine learning pipelines are built around. We study this challenge through a case that is well grounded in psychological theory but rarely modeled computationally: self-compassion, the tendency to respond to one's own setbacks with patience rather than harsh self-criticism. We examine how it appears during structured reflective interviews in a technology-mediated training setting, where people naturally talk through socio-emotionally demanding situations. Since no existing
dataset captures this kind of construct in this kind of setting, we collected and annotated 51 reflective dialog sessions using an independent, temporally overlapping annotation scheme grounded in established theory. We consolidate the underlying six-component psychological model into a three-class supervision space, balancing self-kindness and mindfulness against self-critical or overwhelmed states, and build a reproducible window-based pipeline that aligns
video, audio, and text on a shared timeline. Unimodal models trained on each modality separately are compared against a simple probability-level fusion strategy, which yields modest but consistent gains over the best single modality. We close by discussing where each modality succeeds or struggles, what this suggests about how this kind of construct is actually expressed in reflective
speech, and what would be needed to model it, and constructs like it, more effectively.
Read the full abstract ▾
Computer Vision
Improved Distributional Diffusion Models
Tommaso Martorella, Alexandre Galashov, Felix Krause et al. (+4 more)
Distributional
Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a distributional denoiser trained via a scoring rule objective, learning a
stochastic approximation to $p(x_1 \mid x_t)$ rather than its conditional mean. However, scaling DDMs to modern image-generation settings faces two obstacles: (i) multi-particle training incurs overhead that scales with the number of particles, (ii) DDMs use globally fixed scoring rule hyperparameters, forcing a single trade-off across sampling budgets. We mitigate these limitations by deferring particle expansion to late
transformer layers, and the hyperparameter trade-off by introducing time-dependent scoring rule schedules informed by the dynamical regimes of~\citet{Biroli2024}. Combined with a DiT-based latent setup, these changes make DDM training practical on class-conditional ImageNet-$256^2$, achieving 4.48 FID at 4 steps and 2.38 at 50 steps with DiT-XL/2, from a single model trained from scratch in one stage, without a teacher, self-
distillation or JVPs. The result is a
stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation. Code and pre-trained models available at https://github.com/CompVis/iDDM.
Read the full abstract ▾
All authors Tommaso Martorella, Alexandre Galashov, Felix Krause, Stefan Andreas Baumann, Valentin De Bortoli, Arthur Gretton, Björn Ommer
Artificial Intelligence
From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks
Zheng Zhang, Lufei Li, Xinyue Tan et al. (+4 more)
LLM-as-a-Judge is increasingly used to evaluate policy responses on open-ended tasks that lack ground-truth answers. Existing work often directly converts the resulting judgments into reward signals for policy training, paying limited
attention to intrinsic judgment quality and largely restricting the use of Judges to training-time supervision. We systematically investigate judgment quality and downstream utility by examining both how judgments are elicited and how they are used. For judgment elicitation, we vary the Judge protocol along three dimensions: verdict granularity, critique usage, and evaluation batching. For judgment usage, beyond policy training, we extend Judge to test-time inference through Best-of-N selection, Judge-guided revision, and beam search. We find that, (i) Surprisingly, judgment quality and downstream utility do not always align. (ii) Judge protocol design substantially affects both intrinsic judgment quality and downstream utility. (iii) Judge guidance effectively converts test-time compute into performance gains, with benefits varying across inference strategies. Our results call for a multifaceted evaluation of LLM Judges on open-ended tasks, encompassing intrinsic judgment quality, and downstream utility.
Read the full abstract ▾
All authors Zheng Zhang, Lufei Li, Xinyue Tan, Yuanhao Zeng, Ziwei Shan, Yexin Li, Kan Ren
Software Engineering
LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems
Yun Peng, Zihan Wu, Zeyang Zhuang et al. (+6 more)
Modern coding
agents can deliver increasingly large repository-level changes, and recent
benchmarks reflect this by emphasizing long-horizon tasks with large reference implementations. Many
benchmarks evaluate coding
agents' implementation capability to produce correct code edits from detailed specifications. However, practical modular development tasks also require the perception capability of grounding user intent and high-level design to derive a specification. We introduce LoLBench to evaluate both capabilities through the entire proposal-to-implementation process on large software systems. It is a
multilingual benchmark of 100 tasks across 29 software systems in five domains. Each task provides a human-written enhancement proposal with user intent and high-level design. On average, proposals contain about 5,000 words, software systems contain 2.4 million source lines of code (LoC), and implementation pull requests (PRs) change approximately 5,500 LoC. Across 28
agents we evaluated, the best
agent resolves only 14% of tasks and achieves a 52.7% Fail-to-Pass (F2P) pass rate. Failure analysis identifies incomplete code localization as a major bottleneck, while providing reference-derived file trees alongside API specifications improves resolved rates by 16–22 percentage points (2.4–17$\times$), reaching at most 34%. These results show that both perception and implementation remain central challenges for coding
agents in practical modular development on large software systems. LoLBench is available at https://huggingface.co/
datasets/lolbench26/LoLBench.
Read the full abstract ▾
All authors Yun Peng, Zihan Wu, Zeyang Zhuang, Xin Zhou, Rui Shu, Xu Han, Chun Yong Chong, Yuan Wang, Jiakun Liu
Computer Vision
MSTypography: Multi-character Semantic Typography via Balancing Word Legibility and Object Recognizability
Xinye Yang, Xinding Zhu, Kai Fang et al. (+4 more)
Semantic typography is a design technique where the visual representation of a word conveys its semantic meaning, while maintaining its legibility. Existing digital typography methods mainly focus on single-character scenarios. They suffer from a lack of legibility constraints and insufficient local deformation when extended to multi-character words, as the intricate structures among multiple characters are hardly preserved during the typography process. In this paper, we propose a global-to-local typography framework for multi-character scenarios. It performs mask-driven silhouette approximation at the global level, while semantic-guided refinement at the local level, with a culling step in between to improve efficiency. To preserve word legibility, we designed structural losses (including explicit collision constraints and implicit Jacobian singular value constraints) and an OCR constraint for character-level readability. To enhance the object recognizability, we leverage semantic guidance with
diffusion priors, which drives the character glyph toward the target concept while preserving its structural integrity. To the best of our knowledge, this is the first multi-character semantic typography method that effectively balances word legibility and object recognizability. Evaluations on five representative
languages (English, Chinese, Japanese, Korean, Arabic) demonstrate superiority over SOTA methods. Codes will be open-sourced.
Read the full abstract ▾
All authors Xinye Yang, Xinding Zhu, Kai Fang, Xinyi Ren, Mengjian Li, Bin Cao, Jiazhou Chen
Numerical Analysis
BandPC: Learning Residual-Band Preconditioner Combinations for Flexible Conjugate Gradient Solvers
D. M. Li, Shang-Tian Yang and Xin Qiu
The conjugate gradient (CG) method is a classical iterative solver for sparse symmetric positive definite (SPD) linear systems, but its convergence strongly depends on the spectral properties of the system
matrix. Preconditioning can improve these properties; however, designing preconditioners that generalize across diverse and irregular sparsity patterns remains challenging. We propose BandPC (Band Preconditioner Combinations, where "Band" denotes residual-norm bands), a data-driven framework that leverages graph neural networks (GNNs) to predict multi-stage preconditioning strategies for the flexible conjugate gradient (FCG) method. BandPC partitions the FCG iteration into three residual-norm-based bands and defines a structured search space of 125 candidate combinations over five classical preconditioners. By exploiting FCG's ability to switch preconditioners across iterations, BandPC learns to map
matrix structure directly to a promising preconditioner sequence. To improve training and generalization, we introduce a soft-labeling mechanism that retains near-optimal combinations and normalizes their scores into a label distribution, together with a hierarchical feature representation that captures node-level attributes, edge-level algebraic coupling strengths, and global
matrix statistics. Experiments on a hybrid
benchmark of synthetic SPD problems and diverse
matrices from the SuiteSparse Collection show that BandPC achieves the best iteration count and solution time on 41.3% and 33.1% of test
matrices, respectively, even when compared with each
matrix's individually best traditional preconditioner. These results demonstrate that learned residual-band preconditioner scheduling can effectively accelerate flexible CG solvers.
Read the full abstract ▾
Computer Vision
TaoFlowForge: Progressive Native Mesh Generation via Cascaded Flow Matching
Xianze Fang, Qiyuan Feng, Dongfang Sun et al. (+6 more)
3D content generation technology has significantly advanced the work of designers, as well as the 3D printing and gaming industries. However, it remains difficult to produce lightweight, editable, and topologically clean artistic content that is directly production-ready. To achieve this, we present TaoFlowForge, an artistic mesh foundation model that generates production-ready meshes. Specifically, TaoFlowForge decomposes the mesh generation process into vertices generation and their connectivity prediction, i.e., edges. We formulate vertices generation as a two-stage coarse-to-fine process and incorporate several effective loss functions to further enhance its performance. In the connectivity prediction stage, we propose a simple yet effective method for estimating the connectivity affinity between vertices and additionally predict per-vertex normals, which determines the correct orientation of faces. Besides, we construct a large-scale
dataset combining hand-crafted 3D assets with public high-quality
topology datasets. Based on this, a carefully designed data curation pipeline is employed to filter the raw
dataset, retaining only high-quality
topology data for model training. Our model is trained on the combined
dataset and tested on both out-of-distribution hand-crafted set of 3D assets and public
datasets. Under image-conditioned generation, TaoFlowForge outperforms autoregressive methods and achieves state-of-the-art results among open-source mesh
topology generators. We will release all the code and weights together with a portion of our test
dataset.
Read the full abstract ▾
All authors Xianze Fang, Qiyuan Feng, Dongfang Sun, Yan Zhang, Xiuchao Wu, Jingnan Gao, Jiangjing Lyu, Chengfei Lyu, Gang Yu
Numerical Analysis
Mixed-Precision Computing for Scientific Discovery: Formats, Co-Design, and Responsible Approximation
Emmanuel Agullo, Hartwig Anzt, Daniel Bauer et al. (+37 more)
Reduced and mixed precision have moved from a niche optimization to a central design axis in scientific computing and engineering, driven by energy constraints, heterogeneous accelerators, and the convergence of simulation and machine learning. This paper organizes the landscape around seven coupled themes—number formats, floating-point emulation, emerging architectures, hardware/software co-design, relation to other approximations, software design, and precision as a multilevel resource —and, for each theme, synthesizes the state of the art, future directions, and open questions. We emphasize energy per trusted solution as the core objective, and we frame \say{recklessly responsible} computing as a pragmatic doctrine: exploit low precision aggressively, but with systematic detection, escalation, and certification pathways.
Read the full abstract ▾
All authors Emmanuel Agullo, Hartwig Anzt, Daniel Bauer, David Bindel, Alfredo Buttari, Alexandru Calotoiu, Erin Claire Carson, Pasqua D'Ambra, Ieva Daužickaitė, James W. Demmel, Jack Dongarra, Iain Duff, Massimiliano Fasi, Dominik Göddeke, Stef Graillat, Laslo Hunhold, Roman Iakymchuk, Fabienne Jézéquel, Nils Kohl, Harald Köstler, Jakub Kružík, Julien Langou, Xiaoye Sherry Li, Hatem Ltaief, Piotr Luszczek, Yuxin Ma, Theo Mary, Mantas Mikaitis, Hiroyuki Ootomo, Daniel Osei-Kuffuor, Enrique S. Quintana-Ortí, Ulrich Rüde, Jennifer Scott, John Shalf, Linda Stals, Rasmus Tamstorf, Stefan Turek, Petr Vacek, Bastien Vieublé, Rio Yokota
Computer Vision
Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition
Yi-Pei Chiu and Wei-Ta Chu
Using
language instructions as conditions to guide
robot policy learning has recently become an important research domain. However, existing
language-guided policy learning methods typically use an overall task description to guide the entire demonstration trajectory. For manipulation tasks involving multiple execution stages, these methods assign the same
language description to different subtasks, making it difficult to distinguish the behaviors required at different stages. In this work, we propose a multi-granularity
language guidance method based on instruction decomposition. The proposed method decomposes an overall task description into more fine-grained, concrete subtask-level
language instructions, thereby enhancing learning efficiency and improving performance. We evaluate the proposed method in the setting of multi-task imitation learning and validate its effectiveness.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from quant-ph
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models
Emily Jimin Roh, Hyojun Ahn, Hoyeong Lee et al. (+4 more)
Frozen
language models (LMs) are increasingly used as fixed feature extractors for downstream reranking, scoring, and preference modeling, raising a practical question: how should a compact module represent interactions among features in a fixed low-dimensional bottleneck? Common linear and low-rank adapters remain linear at the adaptation module itself, whereas explicit second-order alternatives introduce pairwise interactions through direct parameterization or predefined factorizations. We propose SQUARE, a Structured
QUAntum REpresentation adapter that amplitude-encodes the bottleneck vector, applies a parameterized
quantum circuit, and measures the resulting state. We show that each basis-probability feature is exactly a normalized quadratic form in the bottleneck coordinates, while the additional Pauli-$Z$ readouts are signed linear combinations of these probabilities. The measured map can therefore parameterize interactions over $O(d^2)$ coordinate pairs through a small set of shared
circuit parameters, where $d$ is the bottleneck dimension. It provides a structured parameterization within, rather than beyond, the classical normalized-quadratic feature class. In a disjoint same-pipeline evaluation over eight GLUE-derived controlled interaction tasks and five shared seeds, SQUARE achieves an average test accuracy of $0.7565$, compared with $0.7355$ for an affine normalized-quadratic predictor, $0.7271$ for the evaluated parameter-matched Givens mixing model, $0.6817$ for an MLP, and $0.6155$ for a frozen-
circuit control. Under reduced supervision, it also shows consistent gains over the strongest evaluated classical comparator, with the same qualitative pattern across multiple frozen LM backbones. All
circuit experiments use simulation, while the learned feature map can be evaluated exactly in batched PyTorch without
quantum hardware.
Read the full abstract ▾
All authors Emily Jimin Roh, Hyojun Ahn, Hoyeong Lee, Soohyun Park, Sung Whan Yoon, Vaneet Aggarwal, Joongheon Kim
Artificial Intelligence
Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models
Zheng Zhang, Xinyue Tan, Lufei Li et al. (+3 more)
On-policy self-
distillation (OPSD) improves large
language models by letting a self-teacher with privileged information provide dense
token-level supervision on the model's own trajectories. Yet existing methods typically construct the self-teacher from the current, initial, or slowly averaged policy state, leaving the quality of supervision constrained by the teacher's ability to exploit privileged information. We ask whether the model's own optimization progress can instead be recycled into a stronger self-teacher. In this paper, we introduce Bootstrapped On-Policy Self-
Distillation (B-OPSD), which temporarily trains the policy ahead to obtain a future teacher, restores the student to the original policy state, and then uses the future teacher to supervise the restarted student. The future teacher improves supervision in two complementary ways, it can generate more reliable privileged trajectories and, conditioned on them, provide more informative
token-level targets along the restarted student's on-policy trajectories. Experiments on mathematical
reasoning with Qwen3-4B and Qwen3-8B show consistent improvements over standard OPSD in both settings, including gains from 27.50 to 41.30 and from 48.80 to 64.44 in the rollout-privileged setting. Our findings point to a broader principle for self-improving models that future learning progress can be distilled backward, preserving acquired knowledge while bootstrapping beyond the optimization state that produced it.
Read the full abstract ▾
All authors Zheng Zhang, Xinyue Tan, Lufei Li, Xinyi Zhang, Yexin Li, Kan Ren
Robotics
ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning
Shaoyin Luo, Song Wang, Shibo Xia et al. (+5 more)
Human-in-the-loop reinforcement learning (HIL-RL) offers a promising route to efficient training of robotic manipulation policies by combining autonomous learning with human demonstrations and online corrections. However, insufficient use of successful human experience in value learning prolongs costly real-world training, while persistent imitation penalties can limit value-driven policy improvement. To address these limitations, we propose ReF-HIL, an efficient HIL-RL framework that uses human guidance to accelerate the learning process. Human-Reference-Guided Value Shaping learns an independent value reference from successful human experience to guide online value learning, while incorporating local corrective feedback. A Human Action Fence defines a learned human-action neighborhood, allowing value-driven optimization for better performance without imitation penalties inside while constraining policy and value updates outside. Experiments on five diverse and challenging real-world manipulation tasks demonstrate improved overall learning efficiency and higher success rates compared with the evaluated baselines. Specifically, ReF-HIL reaches 90% autonomous success in only 18-63 minutes of active training and achieves final success rates of 91.7-100%. These results highlight the potential of human-guided reinforcement learning to acquire reliable manipulation skills efficiently in the real world. Project website: https://anonymous.4open.science/w/ReF-HIL-7762/
Read the full abstract ▾
All authors Shaoyin Luo, Song Wang, Shibo Xia, Tianle Zhang, Zhaowei Liang, Guanghui Shen, Bin Wang, Dan Wu
Artificial Intelligence
SkillCome: Group Contrast Skill Optimization with Dual Memory
Haolin Li, Feng Hong, Ang Li et al. (+6 more)
Skill
evolution improves the capabilities of large
language models by analyzing trajectories generated under a given skill and modifying the skill accordingly. Existing approaches typically generate a single trajectory per question. However, this provides insufficient optimization signals since it requires inferring effective skill edits from a solitary path. It is difficult to pinpoint which actions caused the failure in a failed trajectory, or to determine which actions in a successful one should be incorporated into the skill. Furthermore, they rely on a local batch of trajectories for analysis, making the optimization direction susceptible to noisy evidence. To address these, we propose SkillCome, a Skill-
evolution method based on group Contrast optimization with dual
memory. For each question, SkillCome generates trajectories and performs group contrast analysis to precisely identify key behavioral divergences between successful and failed trajectories, offering reliable optimization signals. The dual
memory system further accumulates evidence from historical steps to track patterns shared across different groups, leading to more generalized optimization directions. Together, SkillCome builds a systematic optimization process that transforms experience from observed successful trajectories into reusable skills. Extensive experiments on six
benchmarks spanning question answering,
reasoning, and agentic tasks demonstrate the effectiveness of our method. SkillCome consistently outperforms baselines across five models of varying families and scales, with gains up to +5.69 points.
Read the full abstract ▾
All authors Haolin Li, Feng Hong, Ang Li, Chilin Fu, Weichang Wu, Ya Zhang, Yanfeng Wang, Xiaolu Zhang, Jiangchao Yao
Computation and Language
LLM unbranding: Erasing Commercial Identity while Preserving Generic Utility
Kajetan Ożóg, Alicja Wojciechowska, Dawid Malarz et al. (+3 more)
Establishing unbranding as a critical practice to prevent visual logos from acquiring negative connotations is standard in image generation. Large
Language Models (LLMs) now face a parallel and emerging challenge. These models frequently generate brand descriptions within diverse contexts. This frequency introduces significant risks, such as trademark dilution, false attribution, and brand defamation. In response, we formally define the novel task of LLM Unbranding. We specifically address the complex challenge of managing trade dress within textual outputs. This involves neutralizing characteristic
language, slogans, and stylistic markers that define brand identity. Crucially, these elements are less evident than explicit visual logos. To
benchmark this task, we introduce a comprehensive evaluation
dataset incorporating prominent brands from multiple commercial domains. We rigorously evaluate existing state-of-the-art machine unlearning models using this
benchmark. This evaluation identifies their limitations in selective textual unbranding. Finally, we propose MUTE, a novel inference-time method that effectively neutralizes textual trade dress while preserving the LLM's general capabilities and utility. By leveraging an iterative refinement loop, MUTE systematically optimizes system instructions to safely eliminate brand leakage without requiring fragile parameter updates. Code and
dataset: The evaluation
dataset and code for LLM Unbranding are available at https://github.com/KajetanOzog/LLM_unbranding. The implementation of MUTE is available at https://github.com/KajetanOzog/MUTE.
Read the full abstract ▾
All authors Kajetan Ożóg, Alicja Wojciechowska, Dawid Malarz, Paweł Batorski, Artur Kasymov, Przemysław Spurek
Robotics
Adversarially Robust Geometric Safety Certificates for Nonholonomic Robots Against Maneuvering Obstacles
Chandan Kumar Sah, Bazeela Banday and Jishnu Keshavan
Safe
navigation against obstacles that can actively maneuver within bounded capabilities remains challenging: robust control barrier function methods typically treat obstacle actions as generic disturbances, while differential-game approaches are computationally expensive for online
navigation. We propose an adversarially robust
geometric certificate that accounts for the worst-case effect of admissible obstacle maneuvers directly in the safe-set geometry through a closed-form contraction of the certificate parameters. The construction exploits a structural property of line-of-sight (LoS) certificates: the
robot and obstacle actions enter the certificate through a common state-dependent
geometric gain. This gain cancels in the worst-case comparison, reducing the differential game to a direct comparison between obstacle maneuvering capability and the weaker of the
robot's longitudinal and steering authorities. Instantiated on the
parabolic certificate, the construction yields Adversarially Robust Dynamic
Parabolic Control Barrier Functions (AR-DPCBF), for which we establish sufficient conditions for forward invariance of the contracted safe set against all admissible obstacle maneuvers under kinematic bicycle dynamics with bounded inputs. When the obstacle capability is unknown, a sliding-window
estimator supplies a high-probability upper bound, allowing the guarantee to be retained with the corresponding coverage probability. We further formulate soft and buffered variants to recover feasibility in dense environments. Simulations across obstacle capabilities, densities, and capability mismatch show substantial reductions in barrier violations and collisions and demonstrate that pointwise robustification of the barrier derivative cannot substitute for contraction of its geometry.
Read the full abstract ▾
Artificial Intelligence
When Should Agents Check External State? Budgeting Observations for Stored Intentions
Zhengkun Di, Bin Shi, Kai Sun et al. (+2 more)
Prospective
memory allows an
agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition currently holds. Checking it may require web access, multi-step tool use, and paid calls. Existing systems decide when intentions require
attention, but do not allocate the resulting observations under a shared budget. We introduce the first resource-allocation formulation for the external observations required by stored intentions under a shared episode budget. BudgetPM offers two policy variants that share a hard-budget executor. BudgetPM-Static uses a lightweight Logistic scorer to learn whether a check improves the current decision. BudgetPM-Sequential distills full-episode hindsight schedules into a lightweight policy that decides when to spend or reserve capacity using only pre-query information at deployment. We evaluate BudgetPM against two public
memory-
agent systems, five matched controls, and four hand-designed monitoring or budget-adaptation rules. Across two
benchmarks and three backbones, BudgetPM-Static outperforms adapted Mem0 and PMA workflows. On PM-Bench, its Logistic scorer reaches competitive quality–cost operating points alongside higher-capacity scorers and retains 99.9–100% of unconstrained quality with 42–54% fewer observations. Under severe scarcity and the same hard caps, BudgetPM-Sequential exceeds the strongest tested natural monitoring schedule by 1.92–2.58 Set F1 points. It reaches the same Set F1 and on-time recall with 16–33% fewer observations. Matched attribution, exact-cost analysis, and a fixed-budget load intervention link this gain to competition between present and future opportunities. These results yield a demand–capacity design rule: local gating works when capacity covers demand, while future-aware supervision adds value when observations compete across time.
Read the full abstract ▾
All authors Zhengkun Di, Bin Shi, Kai Sun, Yiming Xu, Bo Dong
Computer Vision
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception
Yaoxin Niu, Zhangquan Chen, Yang Zhang et al. (+5 more)
Fine-grained visual perception enables
vision-
language models to distinguish subtle attributes and ground their answers in visual evidence. In high-resolution scenes, processing the whole image at greater resolution spends visual
tokens on irrelevant content, while isolated crops can lose the context needed to interpret the selected evidence. We introduce EviViT, a lightweight attachment that learns where a pretrained
vision transformer should acquire detail. Human visual-search traces supervise a question-conditioned evidence density, which guides regional re-reading from the original pixels and the allocation of visual
tokens. A sparse, coordinate-aware bridge then connects the regional features to the global scene, allowing the host to interpret precise evidence in context. Learned with the host backbone frozen, the attachment serves both the base model and compatible post-trained descendants without refitting. Experiments across nine hosts show consistent gains in average fine-grained accuracy. Matched-budget comparisons further show that EviViT outperforms global-only processing at every tested
token ceiling while using fewer visual
tokens.
Read the full abstract ▾
All authors Yaoxin Niu, Zhangquan Chen, Yang Zhang, Xiang An, Zhumei Wang, Chih-Ting Liao, Hongkun Cao, Ruqi Huang
Machine Learning
Learning the Structure of Triangular Transport Maps
Morten Blørstad, Pekka Parviainen and Berent Ånund Strømnes Lunde
Triangular transport maps provide a flexible approach to sampling-based probabilistic modeling, including density estimation, generative modeling, and
Bayesian inference. They transform an unknown target distribution into a simpler reference through a monotone triangular map. The map structure is defined by a variable ordering and sparsity pattern, which together encode a directed acyclic graph. Map quality can depend strongly on this structure, yet finding a good structure is computationally expensive because each candidate generally requires fitting a different map. A central challenge is therefore to learn density and structure jointly, while keeping computation manageable as dimension grows. We introduce Self-Structuring Transport Maps (SSTM), which learn the map, ordering, and sparsity jointly. We use SoftSort to learn the variable ordering and $L_0$ gates to learn the sparsity, while preserving a triangular structure. To keep the map scalable, we use a monotone BatchEnsemble that shares one weight
matrix across all map components through rank-one adapters. Across synthetic and real data, jointly learning the structure and map gives better density estimates than estimating the structure first. When the structure is identifiable from the density, SSTM matches the density performance of a map fitted with the true structure and outperforms autoregressive flows. On large
datasets, SSTM is competitive with autoregressive flows.
Read the full abstract ▾
Computation and Language
Cross-Linguistic Effects in Bilingual Phoneme BabyLMs
Nikitas Theodoropoulos, Maria Lymperaiou and Giorgos Filandrianos
Cross-linguistic effects are a central topic in bilingual first-
language acquisition. Artificial learners can help investigate L1-L2 interactions by enabling controlled comparisons across
language combinations and learning conditions. Recent work explores this direction by training bilingual
language models under developmentally plausible constraints. However, human and model learners still diverge in fundamental ways, with one major difference being input modality: children learn primarily from spoken input, whereas
language models are typically trained on orthographic text. To reduce this gap, researchers have trained models on phonemic representations of
speech. In this work, we combine these research directions to train bilingual BabyLMs with phonemic input. We keep English fixed as the L2 and vary the L1 across German, Swedish, Persian, and Basque, selected to represent contrasting combinations of syntactic and phoneme-inventory distance from English. Our results show stronger L1-related variation in grammatical learning trajectories under phonemic than orthographic input, while early lexical differences align with phoneme-inventory similarity.
Read the full abstract ▾
Machine Learning
Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training
Hongyang Li, Xiao Li, Caesar Wu et al. (+3 more)
Recent approaches to reinforcement learning (RL) post-training for large
language models increasingly remove the critic to reduce training instability and
memory overhead. Even where a critic is trained, it is discarded once training ends, although it has learned to predict outcomes. We revisit this trend and show that a pretrained critic's ability to predict future outcomes can make it a valuable asset for efficient long-horizon
reasoning. First, we find that instability in critic-based RL for long chain-of-thought
reasoning is largely an optimization artifact: keeping policy updates small and low in variance restores stable convergence. Second, a well-pretrained critic estimates the posterior probability of eventual success from later trajectory states and unfinished prefixes. Its predictions provide outcome-derived, dense, per-prefix learning signals that, during policy optimization, require neither completed rollouts, step-level annotations, nor external reward labels. Building on this insight, we introduce Reward-Free Policy Optimization (RFPO), which repurposes a single calibrated, frozen critic as a rollout-level reward, a value baseline for generalized advantage estimation, and a success forecaster for unfinished prefixes. We further show that binarizing the debiased score stops the policy from exploiting the critic's length bias. Binarized, RFPO matches supervised PPO without a single label in the training loop, while cutting compute and
memory overhead. This makes RFPO well suited to long-horizon
reasoning tasks, where outcomes arrive late and generation dominates cost: because rollouts can be rewarded before they finish, training no longer has to pay for waiting on every trajectory to complete. Our findings challenge the prevailing critic-free paradigm and establish critic-based, reward-free optimization as a scalable and computationally efficient path for LLM post-training.
Read the full abstract ▾
All authors Hongyang Li, Xiao Li, Caesar Wu, Said Mammar, Grégoire Danoy, Pascal Bouvry
Computational Complexity
Three-Color Free-Flood-It on Fixed-Height Grids Is Polynomial-Time Solvable
Yuxuan Zhou
We give a deterministic
algorithm for Free-Flood-It on rectangular grids $P_k\square P_n$ with at most three colors. For every fixed height $k$, it computes the minimum number of moves and an optimal sequence in $N^{O(k^2)}$ time, where $N=kn$. This resolves the previously open three-color case on complete $3\times n$ boards. The proof uses a representation of flooding strategies as paintings by connected regions. We show that an optimal painting can be chosen so that its regions form a rooted tree with strong restrictions on the colors along ancestral paths. These restrictions make the part of the tree visible in any fixed-size connected window admit only polynomially many descriptions. The remaining common ancestors may form an arbitrarily long chain. We retain that chain on a stack and use a finite context-free recurrence to minimize the total painting cost without enumerating all possible stack contents. Connectivity information at the boundary ensures that the resulting local descriptions assemble into one valid global painting. The argument also applies to graphs supplied with an ordering into connected layers of bounded size, provided every edge lies within one layer or joins consecutive layers. A family of three-row boards shows that the unbounded ancestor chains handled by the
algorithm are necessary even for optimal paintings. For any fixed height and palette size, we also give a deterministic EPTAS and a randomized sampling variant with an explicit failure-probability bound. These approximation results use a separate
algorithm with single-exponential dependence on the move budget.
Read the full abstract ▾
Sound
Multichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio
Gouthaman KV, Shiv Gehlot, Vishnu Raj et al. (+2 more)
Accurate perceptual quality assessment is essential for evaluating and optimizing spatial audio, where perceived quality depends on both signal fidelity and inter-channel spatial relationships. However, subjective evaluation is costly, while existing perceptual models are often trained for limited channel configurations and cannot be directly applied to higher-channel-count audio. This raises the question: how can pretrained perceptual knowledge be effectively reused for multichannel spatial audio? Using 5.1-channel audio, we study four levels of multichannel integration: signal, prediction, latent, and feature and propose two learned approaches: latent-level aggregation of spatial-group representations and the feature-level Feature-Band Group
Attention (FGAtt), which adaptively fuses spatial groups at the feature level before perceptual processing. Across five 5.1-channel test sets, FGAtt achieves the strongest over- all performance, demonstrating the effectiveness of feature-level adaptation for reusing pretrained perceptual knowledge
Read the full abstract ▾
All authors Gouthaman KV, Shiv Gehlot, Vishnu Raj, Lars Villemoes, Arijit Biswas
Computer Vision
NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting
Pratik Singh Bisht and Andreas Kolb
We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key driver of representation redundancy. In standard 3DGS, low-order spherical harmonics (SH) are used, restricting the splats' ability to model high-frequency directional effects, which is typically compensated by increasing the number of splats. We propose NRF-GS: Neural Residual Fields for Gaussian Splatting, a hybrid representation that replaces per-splat SH-bases with a shared neural residual field. Each Gaussian encodes a compact set of appearance features and a lambertian base color, while a lightweight global scene-level MLP predicts view-dependent residuals conditioned on viewing direction, distance, and per-splat features. This formulation enhances directional reflectance modeling by combining diffuse per-splat reflectance representations with a shared global function for high-frequency details, enabling both higher expressiveness and parameter sharing across splats. Our key insight is that by accurately capturing high-frequency directional reflectance, especially in specular regions, the GS-representation becomes more expressive, reducing the need for geometrically redundant splats. As a result, NRF-GS achieves comparable or better rendering quality while reducing the number of Gaussians by up to 50%, and produces visibly improved specular and high-frequency details.
Read the full abstract ▾
Machine Learning
Interpretable intrinsic dimension estimation through componentwise calibration of distance and angle
Chih-Hsuan Huang, Chih-Wei Chen and Szu-Chi Chung
DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches state-of-the-art accuracy on clean intrinsic-dimension (ID)
benchmarks. Practical data, however, introduce neighborhood-relative noise and sample-amplitude heterogeneity that can distort these
geometric signals. We reformulate DANCo componentwise, retaining separate distance and angular discrepancy curves so that the source of an estimate can be identified and interpreted. For the distance component, we derive a closed-form Kullback-Leibler divergence for the generic-order ratios of the generalized ratios ID
estimator (Gride); when both angular parameters are matched (Full), Gride reduces mean percentage error from $27.7\%$ to $17.6\%$ at noise equal to $40\%$ of typical neighbor spacing on 24
manifolds. For the angular component, two sampling regimes motivate aligning mean direction while retaining concentration matching (Profiled). On a Gaussian scale mixture with generating dimension 70 embedded in 100 dimensions, profiling raises the Minimum Neighbor Distance (MiND) estimate from $22.8$ to $66.7$, while removing the known amplitudes restores MiND-Full to $71.9$; the control thus attributes the Full shortfall to amplitude heterogeneity. On CIFAR-10 and ImageNet, amplitude-reducing normalizations move angular location toward the references and narrow the Full-Profiled gap, an observational counterpart to the controlled mixture. Across four pretrained convolutional neural networks, Gride-Profiled, the two-nearest-neighbor
estimator (TWO-NN), and the maximum-likelihood
estimator (MLE) exhibit similar rise-and-fall profiles, while Full-Profiled differences identify the layers most sensitive to angular calibration.
Read the full abstract ▾
Machine Learning
Neural Constitutive Learning for Generalized Reaction-Diffusion Systems
Shang-Ke Chen, Yu-Peng Wang, Shih-Hsuan Hung et al. (+4 more)
Generalized reaction-
diffusion systems encompass diverse transport mechanisms and coupled reaction kinetics. A central question for neural PDE solvers is what should be learned so that a common interface can accommodate phase-field and degenerate transport, local reactions, and multispecies coupling. We propose the Neural Constitutive Laws–Mass-Compression-Transport (NCL-MCT) Solver, which learns PDE-specific constitutive responses while retaining temporal
evolution in a shared MCT integrator. Transport is represented through mobility and thermodynamic driving force, and reaction through relative reaction rates. These constitutive responses depend on the current density rather than explicitly on the initial condition or elapsed time, motivating their reuse across different initial conditions and time horizons. The same interface supports velocity-data supervision and known-law supervision, neither of which requires time integration during training. When constitutive laws are known, supervision can be evaluated on independently sampled density fields, enabling trajectory-free constitutive learning without generating solution trajectories. Across seven systems, separately trained constitutive modules share the same interface and MCT integrator and achieve relative rollout $L^2$ errors of $10^{-4}$ to $10^{-2}$. Tests with unseen initial-condition families and an extended time horizon assess reuse beyond training conditions, while separate experiments demonstrate trajectory-free constitutive learning. These results support constitutive responses as an effective learning target for a shared neural PDE framework.
Read the full abstract ▾
All authors Shang-Ke Chen, Yu-Peng Wang, Shih-Hsuan Hung, Wei-Fang Sun, Chao-Shun Zhan, Simon See, Min-Jhe Lu
Artificial Intelligence
Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents
Qi Zhou and Yuanfan Li
Long-horizon LLM
agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Existing group-based methods such as GRPO and GiGPO alleviate this issue by comparing rollout returns or repeated anchor states, but they still fail when the compared returns have no variation. We identify this failure mode as zero-credit failure: during early training, many failed rollouts contain useful prefixes, yet existing methods assign them no task-discriminative advantage. To address this issue, we propose Milestone Viability Potential Policy Optimization (MVPO), a potential-routed policy optimization
algorithm that learns from viable failure prefixes. MVPO estimates prefix potential over Union-Find viability regions, repairs zero-credit groups with potential-difference advantages, and attenuates the potential branch according to relative performance progress. Experiments with Qwen2.5-1.5B-Instruct show that MVPO outperforms eight strong baselines, including GRPO and GiGPO. Under the same training length, MVPO improves over the GiGPO baseline by +4.4 success points on ALFWorld and +5.3 on WebShop, while adding only 0.16%-0.20% advantage-construction overhead.
Read the full abstract ▾
Human-Computer Interaction
Designing a Boundary Negotiating Artifact for Collaborative Socio-Technical Sense-Making in AI Regulatory Sandboxes
Idoia Landa-Oregi, Tom Deckenbrunnen, Alessio Buscemi et al. (+2 more)
The rapid, unpredictable advancements in AI system capabilities has seen regulators take adaptive and experimental approaches to policymaking. Established in other domains as instruments balancing regulation with innovation, regulatory sandboxes are seen as solutions for AI regulation. However, analyses mostly focus on the legal and institutional design of AI Regulatory Sandboxes (AIRSes). With the legal framework leaving the socio-technical interpretation to stakeholders, this creates a gap on the sense-making required to fulfill the AIRS purpose. In this paper, we approach this by designing a Boundary Negotiating Artifact as a way to mediate meaning in AIRSes. Through Research-through-Design we iteratively develop a tool, providing an interface for the different stakeholders to collaborate in AI assessment. We then position it as technical backbone in established AIRS frameworks, structuring the collaborative sense-making of the involved stakeholders. We further report the insights gained from our design process leaving the qualitative evaluation for future work.
Read the full abstract ▾
All authors Idoia Landa-Oregi, Tom Deckenbrunnen, Alessio Buscemi, Daniele Pagani, German Castignani
Computer Vision
Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware
Rajit Rajpal, Shahbuland Matiana, Liew Wei Pyn et al. (+12 more)
We present Waypoint 1.5, a real-time
diffusion world model for interactive
video generation on consumer-grade hardware. Unlike general
video diffusion models, interactive world models (iWMs) must respond to dense user controls under strict latency and throughput constraints. Waypoint 1.5 is pre-trained on 100,000 hours of diverse, control-aligned
video game data across hundreds of games, and generates playable
video conditioned on full keyboard and mouse input. The model includes two resolution variants that run across a wide spectrum of consumer hardware. To characterize this unique setting, we distinguish rendered FPS, latent FPS, and control rate. We describe the data pipeline, architecture, training methodology, and runtime system behind Waypoint 1.5. We evaluate interactivity through latency and throughput. Finally, we discuss the safety and ethics considerations unique to iWMs.
Read the full abstract ▾
All authors Rajit Rajpal, Shahbuland Matiana, Liew Wei Pyn, Anmol Agarwal, Ryan Craig, Andrew Lapp, Mithun Hunsur, Sami BuGhanem, Scottie Fox, Aaron Sanders, Carson Poole, Irene Park, Dave Rossi, Spencer Frazier, Louis Castricato