Artificial Intelligence
Equal-information evaluation of credit assignment in modular financial reinforcement learning
Gennadiy Chistiakov and Yury Yanovich
Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss without adding decision-relevant information or improving economic outcomes. We propose an evaluation framework combining equal-information reconstruction controls, fixed-utility comparisons and prespecified downstream guardrails. The framework is instantiated in an attribution-guided modular trading architecture and tested in three controlled studies covering update allocation, supervision-target representation and portfolio risk control. We find that residual-based allocation is exactly reproduced by an ordinary loss-budget control under the disclosed interface; direct shortfall supervision improves component prediction but fails decoded-outcome preservation; and component-wise critic supervision worsens risk-condition certainty equivalent and drawdown relative to scalar supervision under fixed utility. These results identify three distinct evaluation failures: redundant attribution signals, representation-induced prediction trade-offs, and misalignment between component supervision and downstream risk outcomes. A preserved historical engineering case further shows why module-level learning claims require run-level provenance. The contribution is a reusable methodology for evaluating credit assignment in expert systems operating under partial observability, delayed feedback and economic risk constraints.
Read the full abstract ▾
Logic in Computer Science
Solving Distributed Flexible Job Shop Scheduling Problem Using SAT
Phuong Dang Anh, Duc Nguyen Kim Trung and To Van Khanh
The Distributed Flexible Job Shop Scheduling Problem (DFJSP) requires the joint determination of factory assignment, machine selection, and operation sequencing to minimize the makespan. This paper presents an exact SAT-based approach built on an efficient SAT formulation that exploits problem structure through propagation,
symmetry breaking, and incremental SAT solving to effectively address these coupled decisions. The proposed method is evaluated on 76 standard
benchmark instances from the Fattahi, Brandimarte, and rdata
datasets under two- and three-factory configurations. Together with previously established results, the new SAT optimality certificates bring the total number of proven-optimal instances to 72 out of 76, including three newly certified instances; for two of these instances, SAT also improves the previous best-known makespans. Across the
benchmark configurations, SAT achieves the best results on four of the five configurations and remains competitive with strong exact approaches such as CP and LBBD1_CPIL, as well as existing metaheuristic methods. These results demonstrate that the proposed SAT framework is an effective exact approach for the DFJSP, combining strong solution quality with rigorous optimality certification and offering a complementary exact method for future DFJSP studies and evaluations on additional
benchmark instances.
Read the full abstract ▾
Machine Learning
More Domains, No Gains? FLO: Fast-Slow Reciprocal Learning for Multi-Domain Graph Pre-training
Yupeng Tong, Lianze Shan, Jitao Zhao et al. (+2 more)
Inspired by the great success of foundation models in the development of artificial general intelligence, Graph Foundation Models (GFMs) have recently attracted significant
attention and have the potential to advance graph intelligence. Exhibiting such intelligence requires effectively learning knowledge from large-scale, multi-domain graph data during pre-training. Increasing domain diversity during pre-training is expected to yield richer and more generalizable knowledge. Most existing methods pursue this goal by designing domain
alignment strategies that help a single graph model learn from multiple domains. However, we observe that existing methods struggle to benefit from increasing domain diversity. Through empirical and theoretical analysis, we reveal two key limitations. Firstly, pre-training in most GFMs is confined to a single message-passing paradigm. Since propagation flattens relations among neighboring nodes, the graph model can hardly perceive the knowledge beyond propagation, namely the attribute-predictable component of these relations. Secondly, domain
alignment strategies often rely on randomly initialized parameters that are jointly updated with the graph model using immediate loss feedback, leaving early knowledge acquisition vulnerable to cross-domain interference. To address these issues, we propose FLO, a Fast–sLow reciprOcal approach for multi-domain graph pre-training. Specifically, a propagation-free attribute branch predicts the graph model's relations without message passing and returns these predictions to refine the model. We further stabilize knowledge acquisition by pairing a fast process that adapts to the current domain with a slow process that integrates knowledge across domains. On 12
datasets, FLO benefits from increasing domain diversity and achieves the best average performance in cross-domain and cross-task transfer.
Read the full abstract ▾
All authors Yupeng Tong, Lianze Shan, Jitao Zhao, Di Jin, Dongxiao He
Robotics
BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries
Jiaxin Fang, Ruitong Liu, Zeyu Lai et al. (+6 more)
World Action Models (WAMs) commonly couple
video and action experts through dense, layer-wise Mixture-of-
Transformers (MoT)
attention, exposing action prediction to irrelevant visual features while enforcing matched expert depths. This coupling hinders selective visual-feature use and introduces redundant computation. We introduce Bridge-of-Experts (BoE), instantiated as BridgeWAM, which aggregates visual,
language, and proprioceptive priors through 32 Latent Bridge Queries (LBQs) into a shared, limited latent space. Joint
video-action supervision lets action gradients guide the
Video Expert toward representations better suited for action prediction, while the Action Expert learns to selectively retrieve task-relevant information through cross-
attention. Decoupling expert depths and reusing LBQs during action denoising yield a 5.06B model with a 30-layer
Video Expert and a two-layer Action Expert, achieving 98.25% success on LIBERO and 72.24% pooled success on LIBERO-Plus, demonstrating effective task execution and strong generalization with an ultralight action head. Ablations support joint representation adaptation and unified LBQ conditioning. Relative to Fast-WAM, BridgeWAM reduces single-sample inference FLOPs by 28.72% in simulation profiling and real-
robot latency to 77.1 ms (a 2.47-fold speedup). Qualitative experimental results further indicate preferential
attention to target objects and task destinations across perturbations.
Read the full abstract ▾
All authors Jiaxin Fang, Ruitong Liu, Zeyu Lai, Xingyu Wang, Mingyuan Jia, Pingyue Sheng, Weikang Wan, Mengdi Xu, Yuxiang Gao
Artificial Intelligence
SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability
Xianglong Yan, Zenan Wu, Kewei Zhang et al. (+2 more)
Extreme low-bit weight-only quantization is an effective approach to reducing the deployment costs of large
language models. Below 3 bits, scalar quantization often suffers severe accuracy loss, while vector quantization (VQ) better preserves accuracy through more expressive joint encoding. However, existing VQ methods still exhibit substantial degradation on real-world tasks, and two design challenges remain underexplored: (1) protecting sensitive weight channels within jointly encoded vectors; and (2) allocating a fixed bit budget among representation components, such as direction and radius, to suit different weight
matrices. To address these challenges, we propose SAGE: Split Adaptation and Grouping by Energy for weight-only vector quantization. First, Energy-Stratified Grouping (ESG) couples channel grouping with activation-weighted fitting, grouping channels from different energy tiers within each subvector to prioritize sensitive channels. Second, Adaptive Bit Split (ABS) balances direction-codebook capacity and radius precision per
matrix, selecting the split with the lowest activation-weighted reconstruction error under a fixed budget. Across
benchmarks covering knowledge, mathematics, code generation, instruction following, and tool use, SAGE achieves state-of-the-art performance in the 2-bit quantization setting. On Qwen3-30B-A3B, it retains 95.3% of the BF16 model's average
benchmark score. With our custom-designed CUDA kernel, SAGE delivers up to a 2.55-fold non-streaming end-to-end speedup over FP16. The code is available at https://github.com/Zincwolf/sage.
Read the full abstract ▾
All authors Xianglong Yan, Zenan Wu, Kewei Zhang, Kaicheng Yang, Yulun Zhang
Computer Vision
Japanese Handwriting Generation Based on Human Preference Feedback Using Direct Preference Optimization
Wakana Kuwata, Ryota Mibayashi, Masanori Tani et al. (+1 more)
We propose a Japanese handwriting generation framework that integrates human preference feedback using Direct Preference Optimization (DPO) to align generative models with human cognitive and stylistic preferences. While font generation technologies leveraging Generative
Adversarial Networks and
diffusion models have advanced significantly, applying these approaches to handwriting generation presents unique challenges. Font generation is a deterministic process yielding consistent styles. Handwriting generation, on the other hand, is inherently non-deterministic. In handwriting, glyph shapes never match exactly even when the same writer writes the same character. We define this shape difference as handwriting variability. Although this variability is essential for conveying the natural quality of human writing, it complicates model training and substantially increases data collection costs to capture diverse distribution patterns. To address these limitations, we incorporate human perceptual feedback into the training loop of handwriting generation. While collecting extensive handwritten data is costly, evaluating pairwise preferences between two generated samples remains very easy for humans. Applying DPO, an efficient RL-free preference optimization method, to our generation model enables high-quality handwriting generation without relying on large-scale
dataset collection. Experimental results across four distinct Japanese handwriting styles demonstrate that DPO-based training enhances overall structural accuracy. However, in highly complex styles with significant variability, such as brush pen writing, the model fails to capture style-specific features. These findings highlight a critical challenge in extending DPO to complex handwriting styles.
Read the full abstract ▾
All authors Wakana Kuwata, Ryota Mibayashi, Masanori Tani, Hiroaki Ohshima
Software Engineering
TileCas: Cascading Kernel Development Across Programming Abstractions
Xinyu Xiao, Zihe Song, Dezhi Ran et al. (+2 more)
Programming abstractions have traditionally been designed for humans, but code generation is increasingly performed by models and autonomous
agents. We investigate abstractions for machine-driven programming through GPU and AI-accelerator kernel generation. High-level domain-specific
languages (DSLs) simplify search by delegating implementation details to compilers, while lower-level representations provide finer-grained control at the cost of a larger and more complex search space. In this paper, we present TileCas, a unified, pluggable interface that enables coding
agents to develop kernels across multiple editable abstraction levels. Rather than committing to a single representation, TileCas allows an
agent to transfer and refine candidates across levels through Cross-Level Diagnosis, which maps correctness and performance feedback to actionable controls at different abstraction levels; Abstraction Scheduling, which selects both the candidate and representation from which subsequent refinement should proceed; and a Heterogeneous Search Tree, which preserves and revisits alternative search trajectories spanning multiple representations. We integrate TileCas with two code
agents AKO and KDA, and evaluate both integrations on 50 end-to-end KernelBench Level 3 workloads across two accelerator platforms and two
language models. Giving equal weight to the four accelerator-model configurations, AKO with TileCas achieves an arithmetic-mean speedup of $4.84\times$, compared with $3.75\times$ for the strongest evaluated baseline without TileCas, an improvement of 29.0%. Integrating the same interface with KDA improves its mean speedup by 69.2%, with gains in every configuration. These results show that allowing coding
agents to navigate across programming abstractions can improve machine-driven software development and can be reused across different base workflows.
Read the full abstract ▾
All authors Xinyu Xiao, Zihe Song, Dezhi Ran, Wei Yang, Tao Xie
Programming Languages
(Implicitly) Characterizing Probabilistic Polynomial Time as Used in Cryptography
Ugo Dal Lago and Giulia Giusti
In this paper, we show how a recently introduced $\lambda$-calculus for randomized computation, called $\lambda\mathbf{BLL}$, can accurately capture the notions of first- and second-order polytime computations used in cryptographic definitions and proofs. These results, spelled out in the style of so-called implicit computational complexity, imply that $\lambda\mathbf{BLL}$ is sufficiently powerful to express experiments and adversaries as used in cryptography, and that reductions, when formulated within the calculus, are guaranteed to be complexity-preserving. Remarkably, while
polynomial-time soundness holds for the full calculus,
polynomial-time completeness already follows in presence of a minimal finite set of basic functions.
Read the full abstract ▾
Multiagent Systems
Ehud Shapiro
Grassroots platforms are designed to be owned, operated and governed by their participants, and thus are constituted from person-to-person smartphone apps that are run by the participants. A grassroots app is specified using a grassroots social contract, which is compiled through an abstraction cascade into a volition-guarded Grassroots Logic Program (vGLP), a multiagent concurrent logic programming
language. A vGLP program in turn specifies a smartphone UI via which people express their volitions and thus control the app. Prudence dictates large-scale evaluation and testing of grassroots platforms prior to deployment, but using the many people needed to do that is a contradiction in terms. Hence another solution is needed. Here, we present
stochastic GLP (sGLP), designed to allow grassroots platforms to be simulated at scale from the vGLP programs that deploy them, with
stochastic agents in place of people. sGLP is GLP with a rate extension for specifying
stochastic behaviour. A
stochastic agent is an sGLP program replacing both the vGLP UI and the person behind it. It is typed by the dual of the interactive type of the UI and specifies a
stochastic profile of a person's behaviour. We demonstrate sGLP on the grassroots social graph, with a population of men and women drawn from four
stochastic profiles — homophile or indifferent, wary or sociable — and on grassroots currencies, with four profiles — spenders or savers, cautious or generous — and report what the mix of profiles does to the social graph that forms and to the currencies that circulate. We prove that every run of a vGLP program in which sGLP
agents replace the UI and the people behind it is a vGLP run. We implemented sGLP in GLP by Gillespie's method, and ran reproducible simulations with it.
Read the full abstract ▾
Machine Learning
PTGPO: Prefix Tree Group Policy Optimization
Ruolin Chen, Yang Li, Jihang Wang et al. (+4 more)
Training
language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate actions. Existing group-based methods either assign a shared trajectory-level advantage or estimate step-level advantages from state groups, which may conflate the current action with subsequent decisions. We propose Prefix Tree Group Policy Optimization (PTGPO), a critic-free method that constructs prefix trees over trajectory suffixes within anchor-state groups. PTGPO assigns each tree edge a credit given by the difference between its child and parent empirical mean returns, capturing the conditional return change revealed by each additional action. These prefix-tree credits provide fine-grained learning signals without requiring a critic or additional rollouts. Experiments on interactive
benchmarks ALFWorld, WebShop and Sokoban show that PTGPO consistently improves over RL baselines, demonstrating its effectiveness.
Read the full abstract ▾
All authors Ruolin Chen, Yang Li, Jihang Wang, Zhuoya Zhao, Yuchen Liu, Jiaming Xu, Qian Zhang
Artificial Intelligence
Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
Zhongnian Li, Shi Xu, Peng Ying et al. (+3 more)
Optimization by PROmpting (OPRO) directly leverages Large
Language Models (LLMs) to generate candidate solutions through natural-
language prompting. However, OPRO's optimization process is difficult to track, which prevents LLMs from capturing useful information accumulated over previous iterations, thereby limiting solution quality. To address this limitation, we propose a Tool-Augmented Strategic
Agent (TASA) which summarizes and exploits trajectory to improve solution quality. Specifically, TASA plans the strategy for each step based on the optimization trajectory, which decomposes the optimization process into traceable strategy selections. Moreover, we leverage LLM to construct problem-specific tools and introduce a strategy-guided adaptive tool planner, which efficiently utilizes the information of trajectory to update solutions. We establish local convergence under persistent exploration and evaluate the complete framework under a shared candidate-evaluation budget. The results support its solution quality and the traceability of strategy-guided search.
Read the full abstract ▾
All authors Zhongnian Li, Shi Xu, Peng Ying, Weikang Gong, Zhixiao Wang, Xinzheng Xu
Computer Vision
Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction
Huaizhi Qu, Mingxin Yang, Xintong Han et al. (+2 more)
Set-based variational autoencoders (VecSet VAEs) represent 3D shapes as compact sets of latent
tokens. Although each
token originates from a query at a sampled surface location, whether these latents truly align with geometry remains unclear. We investigate this
alignment and identify four issues: (i)
attention-sink-like
tokens that attract queries from across the shape; (ii) spatially periodic repetitions in decoder
attention responses; (iii) mismatched normal information in encoder and decoder query features; and (iv) missing supervision of the intrinsic relation between signed distance fields and surface normals. To address these issues, we introduce Align-VAE with four corresponding modifications: (i) a shared bank of learnable decoder
tokens provides a workspace for global computation; (ii) distance-biased cross-
attention guides
retrieval toward nearby predicted spatial anchors; (iii) normal-free encoder queries align the two stages' access to normal information while retaining normals in the encoder keys and values; and (iv) a screened Poisson-inspired regularizer supervises surface values and normal-direction derivatives. These changes align latent
retrieval and field prediction with geometry without enlarging the per-shape code. On the ABO
dataset, Align-VAE reduces Chamfer distance by 26.6% compared to the standard VecSet VAE.
Read the full abstract ▾
All authors Huaizhi Qu, Mingxin Yang, Xintong Han, Fangneng Zhan, Chunchao Guo
Robotics
B-Human '26 - Scalable Team Play up to 11 vs. 11
Arne Hasselbring, Tim Laue, Thomas Röfer et al. (+1 more)
B-Human won multiple competitions in the Middle Division of the new Humanoid Soccer League in 2026. In addition to regular matches with three or five players per team, we ventured into uncharted territory by playing demo matches with eleven humanoid
robots, highlighting the tactical flexibility of our behavior and the overall robustness of our system. As B-Human formerly competed in the Standard Platform League with
robots half the size and less than a third the weight, we begin by outlining the adjustments needed for this transition. The central section of this paper details our behavior architecture, drawing on concepts from RoboCup leagues that have used 11 players for much longer.
Read the full abstract ▾
All authors Arne Hasselbring, Tim Laue, Thomas Röfer, Philip Reichenberg
Machine Learning
Muquan Yu and Dihan Hu
Long-term
memory benchmarks for
language agents primarily evaluate whether information from earlier interactions can be retrieved and used when relevant. Persistent
memory systems face an additional problem before future use is known: deciding whether a
memory should remain exact, be compressed, consolidated, or deleted. Existing
benchmarks capture long-range
retrieval, temporal
reasoning, evidence reuse, and incremental interaction, but do not directly evaluate these earlier representation decisions. We formalize
memory lifecycle evaluation and introduce VitaBench, a
benchmark that makes lifecycle decisions measurable through repeated
memory reviews and full-horizon counterfactual evaluation. VitaBench contains a controlled Diagnostic tier that isolates future-use patterns and a Naturalistic tier that composes them into generated customer-service-style interaction streams. We characterize lifecycle decision structure with three diagnostics: lifecycle headroom, measuring the advantage of adaptive choices over the best fixed strategy; horizon reversal, measuring when short-horizon decisions change under delayed consequences; and optimal-action diversity, measuring whether different
memory states favor different lifecycle operations. Across both tiers, VitaBench exhibits substantial lifecycle structure: lifecycle headroom is 1.364 in Diagnostic and 1.405 in Naturalistic, and 60.2% and 56.5% of states, respectively, change their preferred action between short and full horizons. A learned delayed lifecycle policy further improves over the best fixed strategy on VitaBench-Naturalistic, reaching 101.5 versus 83.4 joint utility. These results show that retrieving past information and deciding how it should persist are distinct evaluation problems, and that lifecycle management requires evaluation of the delayed consequences of representation decisions.
Read the full abstract ▾
Information Retrieval
Self-improving data synthesis enables scalable adaptation of embedding models
Zucan Lyu, Rui Tang, Jianlyu Chen et al. (+2 more)
AI
agents require specialised
retrieval across domains and tasks, but adapting
embedding models is constrained by costly manual training-data design. Here we introduce SYNTRA, a self-improving agentic framework that turns a few
retrieval examples into reusable synthesis instructions. Given an unlabelled corpus and a few relevant query-document pairs, SYNTRA infers implicit information needs and relevance criteria, then uses feedback on trial outputs to refine instructions for query generation and relevance assessment. Experiments across 24
datasets spanning 15 domains demonstrate that the same synthesis workflow produces effective training data, benefiting even strong
embedding models with and without existing labelled training sets. Self-improvement strengthens this supervision on all six evaluated tasks, yielding better
retrieval than human calibration on four. The training value persists at larger scales: on MS MARCO,
retrieval gains continue across a 32-fold range of synthetic training-data sizes. SYNTRA thus enables scalable
embedding-model adaptation with minimal human intervention.
Read the full abstract ▾
All authors Zucan Lyu, Rui Tang, Jianlyu Chen, Peisheng Jin, Defu Lian
Cryptography and Security
No, Your Tools Are Not Enough: It's Time to Bring Agents to the Hunt
Ati Priya Bajaj, Xiang Mei, Tiffany Bao et al. (+3 more)
Modern software systems are large and complex, demanding scalable and autonomous techniques for vulnerability discovery. Existing approaches still depend on human expertise for domain knowledge, and on human intervention throughout the process of vulnerability discovery. AI
agents offer us an opportunity to make vulnerability discovery more adaptive, scalable, and autonomous.
Agents bring the ability to make continuous decisions and adapt, and general knowledge that can be augmented. In this paper, we present our experience using AI
agents to find vulnerabilities across diverse programs such as Windows drivers, the Linux kernel, XNU, firmware, and web applications. We use an iterative agentic workflow and find that it generalizes across these targets. We discuss tasks that
agents help with, which were previously challenging, and some future research directions we consider important for advancing autonomous vulnerability discovery.
Read the full abstract ▾
All authors Ati Priya Bajaj, Xiang Mei, Tiffany Bao, Yan Shoshitaishvili, Ruoyu Wang, Adam Doupé
Artificial Intelligence
MHWA: Multi-timescale Hierarchical World-Action Model
Pengcheng Pan, Guoqing Ma, Yuhan Zhang et al. (+4 more)
Autoregressive world models have emerged as a powerful paradigm for sample efficient decision making, yet their open loop rollouts often exhibit increasing drift that leads to error accumulation even within a relatively small planning horizon. Hierarchical temporal abstraction is a natural candidate to mitigate such drift by reducing the effective prediction horizon; however, existing hierarchical designs can introduce added structural and conceptual complexity, sometimes making them difficult to control and limiting gains over flat baselines. To this end, we introduce MHWA (Multi-timescale Hierarchical World-Action model), which employs a strided high level context channel to reduce global context update frequency, effectively curbing the propagation of compounding drift. Crucially, via context aware routing, the gating network dynamically reconfigures a low level mixture of experts by using both global context and current observations, thereby enabling flexible high-low coordination, helping alleviate interference commonly observed in static hierarchies. Empirically, using RLiable's seed-by-game aggregation, MHWA (77M parameters) achieves an IQM human normalized score (HNS) of 0.884 across three training seeds on a 14-game Atari subset using 10% subsampled offline data, outperforming a matched JOWA-70M baseline (0.529) and achieving numerically comparable performance to JOWA-150M while using nearly half the parameters and 70.88% fewer training FLOPs per sequence.
Read the full abstract ▾
All authors Pengcheng Pan, Guoqing Ma, Yuhan Zhang, Yang Chen, Yichen Liu, Ziheng Li, Shan Yu
Computer Vision
LightVAE: Towards Compact and Efficient Video Autoencoders
Shiqiao Gu, Yang Yong, Fengjun Zhong et al. (+5 more)
Latent
diffusion models enable high-quality
video generation, but
video VAE encoding and decoding remain computationally expensive. Existing methods use stage-specific lightweight operators, yet either constrain spatial and temporal computation jointly or remove temporal computation altogether, without distinguishing their compression sensitivities in pretrained Conv3D. To address these limitations, we present LightVAE, a compression framework that exploits redundancy in temporal modeling and network depth. LightVAE exactly reparameterizes eligible causal Conv3D layers into an aggregate spatial response and a difference-driven temporal correction. Based on their distinct compression sensitivities, temporal low-rank compression (TLR) keeps the aggregate spatial kernel dense and applies layer-specific low-rank approximation only to the temporal correction. An algebraically equivalent folded implementation converts the arithmetic savings into practical acceleration. LightVAE further uses width-preserving block
pruning to reduce depth and probe-guided feature
alignment, guided by feedback from a frozen teacher suffix, to recover quality after compression. The framework also extends to
video encoders. Across three
video VAE backbones and two GPU platforms, LightVAE consistently accelerates decoding. For the Wan VAE family, it achieves up to $2.24\times$ and $1.11\times$ the decoding throughput of state-of-the-art efficient VAE decoders on NVIDIA H100 and RTX~5090, respectively, with higher DAVIS PSNR and lower LPIPS. On MiniMax-H3, it achieves up to $2.97\times$ the original decoding throughput while retaining 99.51% of the original model's overall VBench-2.0 score. Our code is available at https://github.com/ModelTC/LightVAE.
Read the full abstract ▾
All authors Shiqiao Gu, Yang Yong, Fengjun Zhong, Ruihao Gong, Chengtao Lv, Xiangyu Fan, Lei Yang, Xianglong Liu
Machine Learning
Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient
Seiji Ishihara
A method integrating policy gradient with fuzzy inference has been proposed. This method, hereafter referred to as the base model, has high flexibility with respect to the configuration of fuzzy inference rules and fuzzy representation. It can also automatically adjust the rule weights and the membership functions in the antecedent and consequent parts using the same framework for learning. In methods that integrate reinforcement learning with fuzzy inference, however, the reward function must be designed in advance. It is therefore useful to add learning-based reward estimation to the base model. This paper proposes a fuzzy control method that integrates a reward estimation mechanism based on the
adversarial inverse reinforcement learning (AIRL) framework into the base model. The generative
adversarial nets (GAN) framework adopted in AIRL, however, tends to suffer from unstable learning. To address this, the proposed method treats the policy of the base model as the generator and also uses the set of membership functions in the policy as the cost function of the discriminator. This configuration allows the discriminator update for reward estimation and the generator update for policy estimation to be performed simultaneously on the parameters shared by both, without estimating a value function. In simulations of an illustrative vehicle speed control task, the proposed method acquired policies with high generalization performance through stable and efficient learning.
Read the full abstract ▾
Artificial Intelligence
Relational Semantic Grounding for Test-Time Discovery
Tianle Liu, Gongbo Cheng, Chenggong Ni et al. (+4 more)
Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones from a continuous unlabeled test stream after deployment. Existing TTD methods mainly rely on visual clustering or prototype comparison, and can only assign anonymous labels to discovered classes, leaving them difficult to interpret in open-world applications. In this paper, we propose SEGA, a Semantic Grounding with Attributes framework for TTD. SEGA leverages large
language models to generate attribute-rich descriptions for known classes and constructs an attribute-anchored visual-semantic space during training. At test time, we introduce Relational Semantic Grounding (RSG), which grounds unknown samples with similar and dissimilar known-class anchors,
prompts the LLM to generate candidate concepts, and reranks them in the learned semantic space. The selected concept is further used for confidence-guided test-time semantic stabilization. By coupling attribute-level semantic
alignment with relational concept grounding, SEGA transforms anonymous test-time clusters into interpretable semantic concepts. Experiments show that SEGA improves TTD baselines with the promise of semantic grounding for open-world.
Read the full abstract ▾
All authors Tianle Liu, Gongbo Cheng, Chenggong Ni, Minming Gu, Tao Zhou, Fuyuan Hu, Fan Lyu
Robotics
CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation
Peizheng Guo, Cheng Zhang, Xingyu Zhang et al. (+2 more)
World Action Models (WAMs) combine action generation with future prediction, allowing predicted futures to support action evaluation and
robot decision making. However, the future associated with a candidate action may contain action-induced and environment-driven changes. Directly evaluating the predicted future may not fully characterize the future change associated with the candidate action. For example, a candidate action that worsens a favorable environmental future may still yield a favorable outcome, while one that improves an unfavorable environmental future may still yield an unfavorable outcome. To analyze this issue, we formulate a Structural Causal Model (SCM) for action evaluation in WAMs. The SCM formalizes how action-induced and environment-driven changes jointly shape future evaluation, and reveals a backdoor path through which environmental
evolution can also affect the future evaluation associated with a candidate action. Intervention and backdoor adjustment account for this path, providing a causal basis for characterizing the future change associated with each candidate action. Based on this analysis, we propose Causal Action-Gain World Action Model (CAG-WAM). For each candidate action, CAG-WAM predicts an action-conditioned future and an environmental future under the same current observation, and defines their evaluation difference as causal action gain (CAG) for characterizing the future change associated with the candidate action. During training, we incorporate CAG into Group Relative Policy Optimization (GRPO) to guide
robot policy learning. During inference, we evaluate the initial action with CAG and, when needed, revise it using predicted future information. Experiments on multiple
benchmarks support the effectiveness of CAG-WAM.
Read the full abstract ▾
All authors Peizheng Guo, Cheng Zhang, Xingyu Zhang, Changwen Zheng, Wenwen Qiang
Numerical Analysis
Stochastic Geometrically Exact Beams: Continuous-Time Geometric Principles and Variational Discretizations
Minghang Du, François Gay-Balmaz, Tianzhi Li et al. (+1 more)
Geometrically exact beams naturally arise in physical phenomena and engineering practice for modeling flexible structures, such as soft robotic manipulators and DNA structures. To the best of our knowledge, there appear to be no
geometric integrators for
stochastic geometrically exact beams in a variational formulation. In this paper, we introduce variational principles for the dynamics of
stochastic geometrically exact beams, in both continuous- and discrete-time settings. By introducing perturbations via
stochastic potentials and
stochastic kinematics, we derive the equations of motion from a variational viewpoint. The resulting
stochastic geometric integrators simultaneously discretize time and space in a parallel manner, which provides a distributed computational framework for solving the
stochastic dynamics of complex beam systems. In particular, the proposed integrators are shown to be a
stochastic extension of the well-known deterministic staggered leapfrog scheme for the wave equation, and also a
stochastic extension of Yee's scheme for spatially one-dimensional computational electromagnetism. Numerical results are shown to demonstrate the effectiveness of the proposed approaches.
Read the full abstract ▾
All authors Minghang Du, François Gay-Balmaz, Tianzhi Li, Donghua Shi
Machine Learning
Multi-Token Random-Walk Learning via Meeting-Triggered Information Exchange
Taichun Yeh and Xingran Chen
Random walk (RW)-based
algorithms are widely used in decentralized learning due to their low communication overhead and scalability. While most existing methods rely on a single
token, multiple
tokens can explore the network in parallel and exchange information upon meeting. However, the fundamental benefits of such meeting-triggered interactions remain unclear. In this work, we investigate multi-
token RW learning under two information exchange policies: Average-Gradient and Average-Model, which average
stochastic gradients and updated models, respectively, when
tokens meet. We establish iteration complexity lower bounds for non-convex, convex, and strongly convex objectives on complete graphs, which apply to both exchange policies. Compared with single-
token RW learning, the scaling factor in these bounds is reduced by a factor of $m^2$ for non-convex and convex objectives, and by an exponentially in $m$ for strongly convex objectives, where $m$ denotes the number of
tokens. Numerical experiments reveal distinct behaviors of the two policies under two performance criteria: mean-
token loss (the average loss across all
tokens) and best-
token loss (the minimum loss across all
tokens). Average-Model achieves lower mean-
token loss and is relatively insensitive to the network-to-
token ratio $N/m$, where $N$ is the number of nodes. In contrast, Average-Gradient achieves lower best-
token loss but exhibits a trade-off between parallel exploration and gradient interference as $N/m$ decreases.
Read the full abstract ▾
Robotics
C2Flight: A Closed-Loop Co-Simulation Framework for Early-Stage Evaluation of Heterogeneous UAV Computing Systems
Xizhu Chen, Shuyuan Zhang, Yixuan Li et al. (+4 more)
Early-stage design of heterogeneous
UAV computing systems requires evaluating how
algorithm, hardware, communication, and system
topology affect closed-loop flight before the complete system is available. However, design choices interact through the robotic feedback loop, making task performance difficult to predict from isolated component metrics, while existing execution-driven approaches postpone system-level design feedback until the computing system is integrated. This work presents C2Flight, a closed-loop co-simulation framework that represents target systems as parameterized dataflow graphs and integrates models of hardware under design with independently accessible physical hardware through a unified node interface. Its graph runtime captures the combined effects of buffering, activation, resource sharing, communication, and local timing on closed-loop flight behavior. Validation against onboard and wireless offboard physical computing pipelines confirms its timing fidelity and closed-loop prediction accuracy. Two case studies demonstrate early-stage exploration of deployment and accelerator bit-width choices. These results show that C2Flight exposes system-level design trade-offs before full-system integration, enabling rapid early-stage design refinement.
Read the full abstract ▾
All authors Xizhu Chen, Shuyuan Zhang, Yixuan Li, Huazhong Yang, Yu Wang, Jincheng Yu, Hongyang Jia
Hardware Architecture
"Is Low Power Enough?" Rethinking Energy Efficiency in High-Fidelity Sensing
Chae Young Lee, Lan Mei, Jesse Fonseca et al. (+1 more)
For two decades, long-lived sensor nodes have been built from the lowest-power parts, because their scalar readings take only milliseconds to acquire and send. Scientists now want higher fidelity data from the field, such as images and audio, and these observations break that rule: a low-power microcontroller stays awake for seconds to read, store, and transmit each one, so low power is no longer low energy. We argue that long-lived, high-fidelity nodes should instead be built around a more capable microcontroller, provided the whole board sleeps deeply. We revisit two principles from early sensor networks, "race to sleep" and "talk less", for high-fidelity data and on-device AI, and test them by comparing the STM32N6, which pairs a fast core with a neural accelerator, against the low-power Apollo4 Plus. Although the STM32N6 draws 1.9x more power, it completes an observation (capture, storage, on-board detection, and a LoRa transmission) 9.9x faster and so uses 5.2x less energy. On the same model, it runs inference with 3.2-11.4x less energy, and it fits models over 23 points more accurate. A high-fidelity node lives longest when it finishes quickly, sleeps deeply, and sends only what matters.
Read the full abstract ▾
All authors Chae Young Lee, Lan Mei, Jesse Fonseca, Zerina Kapetanovic
Computer Vision
PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
Zewei Xin, Qinya Li, Chaoyue Niu et al. (+1 more)
While
diffusion models achieve impressive image generation capabilities, they suffer from high computational costs, implausible artifacts, and limited adaptability to dynamic or private data due to static, centralized training. To address these, we propose PixARG, a novel
retrieval-augmented generative framework that integrates dynamic real-world image
retrieval into the
diffusion pipeline to simultaneously enhance efficiency and visual realism. Specifically, PixARG constructs a pixel-level affinity map between the user's text
prompt and the retrieved image to guide a heterogeneous noise initialization. By modulating noise intensity across spatial regions, this mechanism preserves semantically relevant structural priors while perturbing less relevant areas, thereby significantly accelerating convergence. To accommodate this spatially non-uniform noise and ensure synchronized generation, we introduce a pixel-wise asynchronous denoising scheduler and a spatiotemporal denoiser conditioned on the affinity map. Furthermore, we derive an affinity-adaptive training objective that elegantly balances deterministic restoration with
stochastic regeneration across pixels. Experiments on LAION and COYO
datasets across offline, online, and user-specific settings show PixARG enhances realism and semantic
alignment while drastically reducing
diffusion steps.
Read the full abstract ▾
All authors Zewei Xin, Qinya Li, Chaoyue Niu, Fan Wu
Machine Learning
DeKoR: Decomposed Knowledge Routing for Efficient GNN–LLM Fusion
Peiyuan Li, Yongqi Huang, Jitao Zhao et al. (+2 more)
Large
Language Models (LLMs) have shown strong potential for text-attributed graph learning by leveraging rich pre-trained knowledge and
language understanding capabilities. Combining LLMs with Graph Neural Networks (GNNs) offers a promising paradigm for expanding the modeling capabilities of graph learning. However, LLMs and GNNs follow distinct learning paradigms, leading to a pronounced mismatch between their knowledge spaces. Such discrepancies make effective knowledge fusion nontrivial. Moreover, existing methods often incur substantial additional computation for only limited performance gains. To address these challenges, we propose DeKoR, an efficient framework for GNN and LLM knowledge fusion. To enable efficient knowledge transfer, DeKoR decomposes LLM knowledge into complementary local and global views and uses the LLM as an offline teacher to distill them into lightweight experts. To enable selective knowledge fusion, an adaptive router learns how much each node should rely on each expert. Extensive experiments on multiple
benchmarks demonstrate that DeKoR outperforms existing baselines on both node and subgraph classification, achieving superior effectiveness and efficiency.
Read the full abstract ▾
All authors Peiyuan Li, Yongqi Huang, Jitao Zhao, Di Jin, Dongxiao He
Computation and Language
Vela: User Behavior as Supervision Sparks LLM Intelligence
Yang Xiao, Yusong Sun, Haoyi Wu et al. (+17 more)
Large
language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems. These applications demand the user dimension of LLM intelligence: inferring a person's preferences, intent, and likely future actions from weeks to years of behavior data. Yet current models are trained on static text or synthetic data, neither of which captures how user behavior evolves over time. Real-world behavior records, already available at scale on content platforms and in personal-assistant
agents, offer a natural supervisory signal. We propose user behavior as supervision and introduce Vela, a framework that converts real user behavior data into trainable tasks and trajectories. From the anonymized behavior records of 100,000 users, Vela generates 100,000 tasks across 91 real-world task templates; difficulty-based filtering and trajectory acceptance criteria retain approximately 75,000 tasks with selected training trajectories. Fine-tuning Qwen3.6-35B-A3B on these trajectories improves performance over the base model by up to 11.5 points on user-related tasks and by an average of 4 points on general
benchmarks. Training on more user behavior data further improves user-related performance, and reinforcement learning after fine-tuning outperforms reinforcement learning from the base model by up to 7.7 points. These gains suggest that real-world user behavior is a scalable source of supervision for both user-centered capabilities and the broader intelligence of LLMs.
Read the full abstract ▾
All authors Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu
Artificial Intelligence
How to Build a Benchmark That Actually Measures Taste
Xiaofan Wu, Xi Zeng, Miaoxia Chen et al. (+8 more)
Expert-aligned "taste"
benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad
benchmark across visual, brand, book, and tech items under a frozen rubric with expert-only gold (panel n>=3; percent agreement >=0.60 primary gate; weak engagement labels train/analysis-only), together with a control protocol that separates craft judgment from test-gaming. Applying the protocol to a Round-1 pilot (primary_human_expert; three biological human experts; n=250 pairs) surfaces and quantifies three validity threats: two construction artifacts that inflate the trivial-baseline layer, and a difficulty ceiling that inflates every score. (1) Position: the preferred item is slot A with probability 0.956, so an always_item_a policy scores 0.956 (fair chance 0.5). (2) Lexical leakage: a filename
token cue scores 0.912. (3) Difficulty ceiling: craft domains show near-ceiling human agreement (book/brand/tech 1.0), and even under A/B randomization (eval_assignment_seed7; gold_side_A ~0.47) all five VLM cards reach 1.0 on craft, with only visual separating (~0.84-0.91; a post-hoc hard subset, n=107, leaves craft at 1.0). The protocol (expert-only gold, a weak-label firewall, side randomization at construction, filename scrubbing, and hard filters) makes each artifact measurable and, for the two construction artifacts, correctable; we release a reference eval harness and a side-randomization tool, and show the tool removes the position skew (0.916 to 0.495/0.505). The result is a calibrated view of what the
benchmark does and does not yet measure: position and leakage are fixable, whereas the craft-domain ceiling is a pair-difficulty limit that Round-2 must address. We do not evaluate engagement, era/circle conditioning, or calibration here, and we claim no general taste SOTA.
Read the full abstract ▾
All authors Xiaofan Wu, Xi Zeng, Miaoxia Chen, Peishan Chen, Shuyan Li, Chen Wang, Xiaohan Wang, Wanling Xu, Jiyun Yao, Hanyong Zhong, Jiahao Zhu
Computation and Language
Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
Rui Hua, Yu Wei, Ziri Jin et al. (+15 more)
Large
language models have advanced medical
reasoning, but clinically grounded
reasoning in traditional Chinese medicine (TCM) remains challenging because prescription decisions require integrating domain knowledge, syndrome differentiation, treatment principles, herbal prescription composition, and dosage determination. We develop a TCM
language model family comprising models with 4 billion, 8 billion, and 14 billion parameters. The artificial intelligence contribution is a staged clinical
alignment framework integrating large scale continued pretraining on TCM and clinical records, complementary
reasoning supervision, and prescription-centered reinforcement learning (RL). We further formulate herbal prescription generation as a structured RL problem with prescription-level feedback, enabling direct optimization of clinical decision outputs beyond knowledge reproduction and generic instruction following. The engineering application is TCM clinical decision support, particularly herbal prescription recommendation. We evaluate the models on a public
benchmark containing 25,620 expert-verified items across 13 TCM knowledge and clinical
reasoning tasks and on a private retrospective
dataset of 4,348 spleen and stomach disease prescription cases. The 14 billion parameter reinforcement aligned model achieves a prescription generation F1 of 37.0 on the public
benchmark, compared with 32.3 for DeepSeek-R1 with 671 billion total parameters, and a herb-level F1 of 52.8 on the clinical
dataset with improved dosage agreement. Reinforcement post-training consistently improves prescription recommendation across all scales, while physician-source analysis shows that expert heterogeneity affects reward stability. These findings demonstrate a scalable pathway from domain grounding and
reasoning supervision to clinically oriented prescription decision support.
Read the full abstract ▾
All authors Rui Hua, Yu Wei, Ziri Jin, Zhuo Sun, Kai Chang, Jianan Xia, Zixin Shu, Xiaodong Li, Dongmei Jia, Fei Dong, Runshun Zhang, Jian Yu, Hao Xu, Haibin Yu, Jiansheng Li, Baoyan Liu, Wenjia Wang, Xuezhong Zhou