Machine Learning
Where Does Randomness Matter in Neural Cellular Automata?
Fei Zuo, Jiaqi Shi and Yujing Liu
Stochastic cell updates are often used throughout the life of a neural cellular automaton (NCA), from backpropagation through time to final rollout. This leaves two questions entangled: does update randomness help learn a useful rule, and must that randomness remain at execution? We separate training and evaluation update modes in controlled Growing NCA experiments, then vary the states shown during training. Under the standard constant-rate persist recipe, asynchronous training passes the short-horizon quality test in 10/10 runs, compared with 3/10 synchronous runs. All ten asynchronous models also retain the target for 4,096 steps under deterministic evaluation. For a scalar translation-invariant
lattice, we derive an exact mean-square criterion: random masking can damp mean modes, but it also injects variance, and a mean-only test misclassifies four non-marginal settings. Finally, among 30 models that all pass the same reconstruction test, eight of ten grow-trained models become off-target at 4,096 steps, while all persist and regenerate models retain the target; damage recovery separates persist from regenerate. The results distinguish optimization reliability, execution mode, and task-specific behavior instead of treating them as one stability property.
Read the full abstract ▾
Databases
Epistemic Typing as a PostgreSQL Table Access Method: Adversarial Conflict Resolution Under Confidence Forgery and Sybil Coordination
Venkata Maguluri, Swapna Kommuri, Kritica Sinha et al. (+1 more)
We describe KNDB, a PostgreSQL 18 table access method (TAM) that types every row with an engine-assigned epistemic kind (MEASURED, INFERRED, or DERIVED) and resolves per-slot conflicts inside every write-time heapam callback. Rows land as ordinary heap tuples; seven of the 44 TAM callbacks are overridden (tuple_insert, multi_insert, tuple_update, tuple_delete, tuple_insert_speculative, tuple_complete_speculative, relation_toast_am), the other 37 delegate to heap; we provide a completeness argument over the interface as a paper artefact. This paper reports the engineering behind that decision and the
adversarial evaluation that motivated it. On a confidence-forgery workload where an attacker asserts INFERRED writes with confidence in [0.95,1.0] against honest MEASURED writes with confidence in [0.5,0.9], KNDB beats a confidence-only baseline by 63 percentage points on the Book-Author fusion
dataset and 92.7 points on the Zheng crowdsourcing
dataset. Both wins are proven load-bearing on the kind axis by a source-rebuild disable-and-test in which the
lattice is neutralised and the win vanishes. Against four truth-discovery baselines (TruthFinder, CRH, CATD, ACCU) reimplemented from the original equations and validated to within 0.3 percentage points of the published numbers, KNDB is competitive below a per-
dataset density-saturation
cell and dominant at or above it. We formalise the
cell as k* ~ rho_alg * h_top, where h_top is per-slot top honest surface-form support, and validate the prediction within +/-20% on Book-Author and +/-30% on Zheng. Because the kind axis is assigned by the engine from independent metadata and cannot be forged at write time, KNDB's k* is unbounded. The paper is honest about where KNDB loses: CRH and ACCU outperform KNDB below saturation on Zheng, and KNDB scores zero on three temporal knowledge-editing
benchmarks whose ground truth is last-writer-wins.
Read the full abstract ▾
All authors Venkata Maguluri, Swapna Kommuri, Kritica Sinha, Ashish Sood
Machine Learning
RAE-PPG: Duration-Grounded Retain-and-Extend Pretraining for PPG Foundation Models
Suyeong Lee, Hochang Lee, Seokyong Sheem et al. (+1 more)
Signal features derived from photoplethysmography (PPG) require different signal durations to characterize. Existing PPG foundation models treat duration as a pretraining or evaluation condition rather than using the different durations required by PPG features to organize self-supervision. We hypothesize that self-supervision should expand with signal duration, allowing a single encoder to progressively acquire additional features while preserving and reusing earlier learning. We introduce Retain-and-Extend PPG (RAE-PPG), which trains a single
Transformer encoder successively on 10 s, 30 s, and 240 s inputs, adding supervision for signal features supported by each longer observation. The encoder is partitioned into duration-specific parameter groups, allowing later stages to reuse earlier groups while updating only the group assigned to the current stage. Selected earlier targets are reused to supervise later stages, encouraging the corresponding features to remain accessible in longer-input representations. Direct decoding from the final encoder shows that earlier features remain recoverable from longer-input representations, while later-stage features show higher mean decoding performance at their introduction durations. Controlled comparisons further show that prior-stage learning provides a better basis for learning newly introduced features at both transitions. Across 18 tasks from eight
datasets, the final frozen encoder achieves the best observed score on 12 tasks compared with five existing PPG foundation models.
Read the full abstract ▾
All authors Suyeong Lee, Hochang Lee, Seokyong Sheem, Daekyum Kim
Numerical Analysis
Hard-Trace First-Order Residual Learning for Coupled Stokes-Brinkman-Darcy Flow
Zefeng Liu and Hongxing Rui
Stokes-Brinkman-Darcy (SBD) models connect free flow and porous flow through a Brinkman layer of finite thickness. The proposed method for solving these coupled equations consists of a mixed first-order formulation, shared interface traces and hard traction constraints, and a pressure correction based on boundary mass balance. Independent stresses, Darcy flux and pressure-gradient auxiliaries avoid second derivatives of network outputs. Boundary liftings and shared traces impose exterior and interface kinematic conditions exactly, while a stress map enforces native Brinkman-Darcy force balance. An integral momentum relation determines the pressure correction after training, without reference-pressure labels. Across two manufactured solutions and three permeabilities, mean corrected upper-pressure relative $L^2$ errors range from 0.87% to 2.58%; correction reduces both upper-pressure $L^2$ errors and the full Brinkman-pressure $H^1$ error in every run. Paired controls assess the contributions of interface sharing and traction enforcement. A non-manufactured filtration problem tests mixed-boundary adaptation against an independently refined finite-element reference, with all four runs satisfying the prescribed field and physical-consistency criteria.
Read the full abstract ▾
Social and Information Networks
Influence Ranking Improvement via Link Addition in Social Networks
Taiki Ikemoto and Sho Tsugawa
Social media platforms increasingly rely on influential users for information dissemination in domains such as marketing and political campaigns. As the value of being recognized as influential grows, users may have incentives to strategically enhance their influence. In this study, we investigate whether and to what extent the influence ranking of a target node can be improved by adding a limited number of outgoing links in the context of influence maximization (IM). We formulate the Link Selection Problem for Influence Ranking Improvement (LSP-IRI) as the problem of selecting a fixed-size set of additional outgoing links from a target node in order to maximize its rank improvement. To examine this problem, we consider two representative heuristic strategies: a greedy method that directly optimizes rank improvement and a computationally efficient random search method. We conduct experiments on four real-world networks ranging from thousands to hundreds of thousands of nodes. The results show that even a few added links can substantially improve IM-based influence rankings. In particular, the greedy method improves the ranks of nodes initially ranked around 50 by several tens of positions on average with only three added links, sometimes moving them into the top 10. The random search method achieves smaller gains under strict budgets but reduces computation time by up to approximately 98% compared with the greedy method and becomes effective when larger budgets are allowed. These findings show that IM-based influence rankings are sensitive to limited local structural modifications and highlight a trade-off between ranking improvement and computational efficiency.
Read the full abstract ▾
Multiagent Systems
GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements
Zhibang Yang, Xinke Jiang, Yuxuan Liu et al. (+9 more)
LLM-based
agents increasingly collaborate with users on long-horizon tasks, accumulating evidence, code, and drafts through extensive search,
reasoning, and execution. As users inspect these results, they may supply missing information requirement completion, introduce new requirements requirement elicitation, or revise existing ones requirement shift. These changes often affect only part of the accumulated work, yet
agents may carry forward obsolete information or turn local revisions into global rewrites. Existing approaches clarify current intent without determining how prior work should change, or reuse execution histories under a fixed objective. We address this gap by formulating dynamic-requirement collaboration as joint requirement tracking and local update. We introduce GitHarness, a pluggable Git-style framework that organizes requirement states and their corresponding harness work states into a branchable version history. A trainable Git
Agent resolves requirement changes and selects a semantically compatible historical state. A unified version interface then restores that state and creates a new branch, enabling the underlying harness to exclude obsolete information, inherit compatible work, and focus execution on affected parts. The Git
Agent is trained through interface-level black-box reinforcement learning, with downstream harnesses and task-execution models kept fixed. We also construct MTAgentBench, a verifier-preserving
benchmark covering mathematical
reasoning, text-to-SQL, agentic search, software engineering, and research synthesis. Experiments demonstrate strong task performance alongside effective requirement tracking, preservation of valid work, and efficient execution.
Read the full abstract ▾
All authors Zhibang Yang, Xinke Jiang, Yuxuan Liu, Mingyu Zhang, Zhixin Zhang, Zhengxing Song, Yue Fang, Guohong Qiu, Ruiqing Li, Xu Chu, Junfeng Zhao, Yasha Wang
Machine Learning
Harnessing Large Language Models to Compile Task-Relevant Context into Bayesian Optimisation
Zhongwei Yu, Sourabh Roy, Bin Cao et al. (+3 more)
Incorporating rich task-relevant context, such as domain knowledge and external observations, is a key capability yet remains challenging for
Bayesian optimisation (BO). Recently, practitioners have started to use large
language models (LLMs) to generate and execute BO programs through coding harnesses. In such emerging practices, the posterior belief is shaped not only by
Bayesian inference but also by LLM-generated model and data artefacts, offering a flexible route for task context to enter BO as executable code. To study whether and how LLMs can be harnessed to compile diverse contextual signals for BO, we formulate LLM-compiled BO as generalised-context decision making. We propose HarBO, a BO-specialised harness that compiles generalised context into the core artefacts of standard BO through a validated multi-stage workflow. Our theory analyses the regret under imperfect compilation and the effect of adding new context. Across synthetic functions and real-world
benchmarks, we find that LLM harnesses can effectively compile context into standard BO, achieving competitive performance with specialised LLM-
embedding-based and direct LLM-in-the-loop BO methods. General coding harnesses can be effective in familiar domains such as hyperparameter optimisation, but fall short in unfamiliar, context-rich domains. Together, these results establish LLM harnesses as a promising, but not automatically reliable, route for making rich task context usable in BO.
Read the full abstract ▾
All authors Zhongwei Yu, Sourabh Roy, Bin Cao, Xue Yan, Anjie Liu, Jun Wang
Multiagent Systems
Regularized policy gradient with learned mixtures of Gaussians for games with continuous actions
Ondřej Kubíček, Viliam Lisý and Tuomas Sandholm
Most successes of superhuman game-playing
algorithms are in games with discrete actions, yet in auctions, robotics, sports, or trading, actions are nearly continuous. Prior techniques either rely on expert-designed discretizations or are sample inefficient. We present a scalable policy-gradient
algorithm for large sequential games with continuous or mixed discrete and continuous actions. It combines
magnetic mirror descent with a mixture of Gaussians reparametrization, trained via self-play. We show that it approximates
equilibrium in games where gradient descent fails. In sequential games, it outperforms neural fictitious self-play and matches or outperforms the final strategies of policy space response oracles with 3.5–5.5$\times$ fewer samples. In heads-up no-limit Texas hold'em, it performs on par with Slumbot.
Read the full abstract ▾
Robotics
TaRL: Learning General and Physical Rewards from Tactile Demonstrations
Po-Yi Wu, Dao-Jan Chang, Shang-Ya Hsiao et al. (+3 more)
Contact-rich manipulation requires
robots to sequence precise contacts, maintain stable grasps, and apply directed forces. Reinforcement learning (RL) can acquire such behaviors automatically, but its performance hinges on reward design: sparse rewards reduce the learning efficiency, while dense rewards are hard to specify. Visual reward learning addresses this by inferring rewards from action-free demonstrations. Because it conditions only on visual observations, it fails to capture rewards beyond visual goals. We propose Tactile Reward Learning (TaRL), a framework that learns rewards from tactile demonstrations. TaRL takes a sequence of tactile deformation maps as input, and regresses task-completion progress from both successful and failed demonstrations. Because TaRL captures local
robot-object interaction, it provides informative feedback to learn firm grasps and correctly directed forces; meanwhile, it is robust to changes in scene layout such as object position. We evaluate TaRL on four manipulation tasks in simulation and two in the real world. Used as a shaping reward, it substantially improves both sample efficiency and final success rate, raising success on Nut threading from 34% to 56% in simulation and on cube pickup from 37% to 97% in the real world. Combining tactile with visual rewards improves performance further. TaRL also generalizes across object instances: trained on box placement and directly deployed to can placement, it significantly improves policy learning on the new task. Project page is available at https://embodiedai-ntu.github.io/tarl.
Read the full abstract ▾
All authors Po-Yi Wu, Dao-Jan Chang, Shang-Ya Hsiao, Hong-Ming Chen, Yu-Cheng Su, Tsung-Wei Ke
Robotics
Scale-Invariant Manipulability Shape Tracking Across Heterogeneous Manipulators
Geunwoo Kwon, Dong-gyu Lee, Kai Li et al. (+2 more)
When transferring manipulability across systems with different sizes and kinematic structures, matching absolute ellipsoid scale may be unnecessary when the goal is to reproduce orientation and semi-axis length ratios. Full-
matrix tracking, however, penalizes both shape and absolute-scale differences, even when only shape matching is required. We therefore propose a scale-invariant manipulability shape-tracking method that treats
matrices differing only by a positive scalar factor as equivalent and uses their unit-determinant representatives. We derive the differential of the unit-determinant shape representative and an orthonormal coordinate representation of the tangent tracking residual under the affine-invariant Riemannian metric (AIRM). The resulting scale-invariant objective is integrated with position and end-effector direction tasks in a constrained joint-velocity quadratic program. Simulations with four heterogeneous
robots evaluate
robot-to-
robot and human-to-
robot transfer. On three followers, the proposed method achieves endpoint shape distances of 9.30 x 10^-5 without scale tuning. With
robot-specific target scales tuned during motion, the Full method retains endpoint axis-ratio errors of 0.19-0.31 on KR500 and UR20. For human reaching with concurrent tasks, the proposed method yields dual force shapes elongated along X like the human target on all four
robots, with endpoint position errors of 2.4-5.6% of reference arm length versus up to 75% for the Full method tracking the original human ellipsoid.
Read the full abstract ▾
All authors Geunwoo Kwon, Dong-gyu Lee, Kai Li, Soonwoong Hwang, Wansoo Kim
Software Engineering
A Heckler in the Hidden State: Correctness Signals in Diffusion Language Models
Angad Miglani, Samrath Singh Chadha, Kevin Li et al. (+1 more)
Diffusion language models generate code by repeatedly updating a partially masked sequence. We ask whether their internal activations encode code correctness and whether that information can improve generation. Across six
diffusion models, linear probes distinguish passing from failing attempts, with the strongest reads generally appearing beyond the early layers. Controls using small semantic mutations support a connection to correctness rather than surface style alone. In comparisons with model confidence, probe point estimates offer no consistent advantage. Adding a probe-derived direction to the residual stream does not yield a dependable improvement in the tested steering settings, while the opposite direction degrades performance. We distinguish these observations from claims about statistical significance or a general inability to steer. Supplementary methods, archived results, and code document the tested interventions and the limits of their statistical calibration and reproducibility.
Read the full abstract ▾
All authors Angad Miglani, Samrath Singh Chadha, Kevin Li, Manas Venkata Sai Ravulapalli
Computer Vision
Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning
Cheng Ye, Weidong Chen, Zhaobo Qi et al. (+2 more)
While
multimodal large
language models (MLLMs) have demonstrated exceptional capabilities in objective understanding tasks, their performance in affective
reasoning still falls significantly short of human standards. We attribute it to a central capability gap: MLLMs are difficult to reliably distinguish semantically proximal
emotions based on fine-grained visual evidence, which could be decoupled as two limitations: 1) Insufficient Attribution. The global
reasoning paradigm of conventional MLLMs severely dilutes fine-grained
emotion cues, where subtle emotional states are usually implicitly encoded, thereby generating emotional misjudgments in complex scenarios. 2) Insufficient Discrimination. Existing methods could only identify regions generally associated with
emotions, which fails to distinguish discriminative regions between semantically similar
emotions, leading to ambiguous
emotion judgements. To overcome these limitations, we present a training-free inference-time optimization framework, named Decoding Affective Nuances (DAN). Specifically, we propose a Hierarchical Emotional
Reasoning Chain (HERC) that enhances the insufficient attribution by harmonizing fine-grained scene/object-level cues and performing a soft-gated
reasoning. Furthermore, to discriminate between semantically proximal
emotions, we design a Contrastive Discriminative Visual
Pruning (CDVP), which isolates discriminative visual
tokens to reason the final
emotion category by computing the absolute discrepancy between the
attention distributions of similar
emotions. Performances on several
benchmarks demonstrate that DAN significantly improves discrimination for affective nuances without consuming additional training resources, especially achieving +10.47% improvements with Qwen3-VL-8B-Instruct on WebEmo25
dataset that contains 25 fine-grained
emotion categories.
Read the full abstract ▾
All authors Cheng Ye, Weidong Chen, Zhaobo Qi, Beier Zhu, Zhendong Mao
Artificial Intelligence
Aperture: Merge-Consistent Rotary States for Compressed Tokens
Yuhao Du and Shunian Chen
Token compression combines content from several positions, yet rotary position
embeddings usually assign the merged
token one coordinate. We ask what positional information must survive later merges. Aperture stores
Fourier moments of the
token's weighted support at the model's rotary frequencies. We prove that these moments have minimal real dimension among continuous states sufficient for the selected expected rotary interactions. Represented mass makes updates additive;
attention normalisation remains a separate readout choice. Uniform intervals give a centre rotation times a sinc gain. We characterise when centres determine interval widths and construct matched examples where they do not. Numerical checks verify the weighted-support implementation. In trained temporal readers, compression transfer varies with gain calibration and feature placement. In a prespecified native
video question-answering comparison, stored support reaches $65.63\%$ accuracy versus $67.12\%$ for the deployed merging rule. These results separate exact positional preservation under compression from downstream benefit.
Read the full abstract ▾
Robotics
DRHeC: Differentiable Rendering for Hand-Eye Calibration with RGB-Based Gradients
Xiaotian Zhang, Yusheng Wang, Naoya Kagawa et al. (+4 more)
Accurate hand-eye calibration is crucial for precision manipulation. Traditional methods rely on markers, with their precision dependent on marker accuracy and observability. In contrast, markerless methods, such as learning-based approaches, use deep neural networks to directly extract keypoints or features from images, enabling the computation of hand-eye transformation with a single image and without the need for physical markers. Recently, differentiable rendering-based methods for hand-eye calibration have leveraged physical models to render binary masks and compare them with observations, enabling hand-eye calibration without fiducial markers in the calibration stage and providing interpretable optimization. While the state-of-the-art differentiable rendering methods achieve remarkable accuracy, the use of binary masks can result in the loss of internal profile details, reducing precision. Additionally, these methods can also suffer from unstable optimization and local minima. In this study, we propose a novel RGB-based differentiable rendering framework that provides richer
geometric and appearance cues by incorporating color and mask
geometric features, thereby improving calibration accuracy and optimization stability. Additionally, we propose a mask-guided image-to-image translation method to ensure explicit preservation of color and
geometric consistency throughout the translation. Our approach is validated through both simulation and real-world experiments, with results demonstrating strong accuracy and robustness and clear improvements over existing differentiable rendering methods. Our method achieves a grasping success rate of 88.9% and insertion success rate of 57.4% on the UR5e real-world experiment, outperforming the state-of-the-art differentiable rendering hand-eye calibration method EasyHeC by 46.3 and 48.1 percentage points, respectively.
Read the full abstract ▾
All authors Xiaotian Zhang, Yusheng Wang, Naoya Kagawa, Noritaka Takamura, Keiji Okuhara, Hiroyasu Baba, Jun Ota
Data Structures and Algorithms
XBDD: A Highly Optimized ROBDD with Per-Edge Variable-Flip Maps
Yinglong Gan, Jintao Yu, Shenggang Ying et al. (+2 more)
The Reduced Ordered Binary Decision Diagram (ROBDD) is a canonical representation of Boolean functions and is widely used in tasks such as equivalence checking and satisfiability checking of combinational
circuits. Classical ROBDD packages greatly improve the efficiency of building ROBDDs through a series of optimization techniques, and compress the node scale of the ROBDD through complement edges. However, existing implementations do not take into account the local polarity differences of isomorphic Boolean functions, and still produce a distinct node for each polarity combination, thereby causing an explosion in the number of nodes. This paper proposes XBDD, a highly optimized ROBDD that, on the basis of fully implementing complement edges and their accompanying engineering techniques, introduces a per-edge variable-flip map. XBDD attaches a flip map to each edge to indicate which input variables must be negated when that edge is followed. This allows nodes that differ only in local input polarities to be merged, further reducing the node count. For certain function families, this sharing even yields exponential compression. We also propose methods that use a bitmap and a map pool to substantially reduce the extra overhead brought by the map, and propose normalization and cofactor operators for the map. In addition, XBDD implements several other engineering optimizations to further improve both time and space efficiency. Experiments show that XBDD trades a controllable time cost for a significant space gain, validating the effectiveness of the per-edge variable-flip map.
Read the full abstract ▾
All authors Yinglong Gan, Jintao Yu, Shenggang Ying, Yusen Li, Xin Hong
Artificial Intelligence
Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes
Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen et al. (+6 more)
Frontier coding
agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely control scene state remains unclear. The generated 3D scene is a persistent, executable artifact: a convincing render can hide incorrect spatial relations, intersecting objects, or unintended modifications. We introduce Code4Scene, a
benchmark of 190 Unreal Engine cases built from human-assembled scenes that evaluates coding
agents on two complementary settings under a shared execution interface. Construction tests scene-level spatial
reasoning from open-ended
language specifications, where many realizations are valid; editing tests precise control of scene state, where the
agent must recover the target scene from reference images while preserving everything else. Rather than scoring code or rendered views, Code4Scene evaluates the generated engine-native scene for task fulfillment, artifact integrity, and static physical validity, with edits additionally compared against withheld ground truth. Across 14 coding-
agent configurations on the 95-case public set, construction and editing performance are strongly correlated but not interchangeable (Spearman $\rho = 0.78$): Claude Fable 5.1 leads construction, Gemini 3.8 Flash leads editing, and GPT-6 Astra narrowly leads overall. Spatial Composition is the weakest construction category for every
agent, while editing remains imprecise: the best Repair F1 is only 0.527, and 35.8% of edits that fully recover the target still introduce unintended changes elsewhere in the scene. These results expose a gap between plausible 3D generation and reliable spatial
reasoning and state control.
Read the full abstract ▾
All authors Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen, Edward Zhang, Zhaoxu Zheng, Yuanheng Li, Yizhao Chen, Tianyang Huang, Lianhui Qin
Computer Vision
Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention
Cheng Ye, Weidong Chen, Peipei Song et al. (+1 more)
Emotional
Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the importance of visual causes to guide
emotion perception and caption generation, they fundamentally rely on simple
attention matching, which inevitably suffers from {causal redundancy and spurious correlations} in co-occurrence bias (e.g., misclassifying “sadness” as “joy” on a sunny beach), leading to severe shortcut learning from confusing backgrounds. Furthermore, existing evaluations fail to verify whether models have genuinely mastered causal
reasoning or merely exploited background confounders. To address these limitations, we first construct {EVC-CauseGround}, a comprehensive
benchmark with dense spatio-temporal causal annotations. Crucially, it introduces a carefully selected {Causal-Faithfulness Subset} to explicitly quantify genuine
emotion-cause attribution. Second, we propose {Causal-EVC}, an
emotion-grounding captioning framework, which introduces a Motion-guided Causal Spatiotemporal Localization module to precisely decouple causal triggers from background confounders. Besides, we introduce an Interpretable Sparse
Emotion Routing module. By synthesizing counterfactual representations and formulating a novel counterfactual contrastive objective, we enforce the model to anchor its
emotion predictions strictly on authentic causal triggers instead of confusing background. Extensive experiments show that Causal-EVC not only achieves the best performance on semantic metrics but also exhibits significant advantages in the causal-faithfulness subset, which demonstrates that our model could mine emotional cues from genuine visual causes and mitigate co-occurrence bias for interpretable
multimodal emotion understanding.
Read the full abstract ▾
All authors Cheng Ye, Weidong Chen, Peipei Song, Zhendong Mao
Computer Vision
DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning
Cheng Ye, Weidong Chen, Bingyan Xu et al. (+1 more)
Reinforcement Learning has significantly advanced the complex
reasoning capabilities of MLLMs. However, prevailing RL
algorithms suffer a severe failure in
emotion reasoning tasks. These methods heavily rely on deterministic hard-label supervision and point-wise isolated evaluation, creating a fundamental gap with the inherently subjective and continuously distributed nature of human
emotions. Furthermore, unlike explicit physical objects, emotional states are deeply implicit within visual cues. This abstract nature exacerbates visual
hallucinations in MLLMs, leading to plausible yet ungrounded emotional evidence. To address these limitations, we propose Diversity-Aware Subjective Policy Optimization (DSPO), a reinforcement learning framework that jointly promotes subjective affective coverage and visual grounding. First, we construct a context-grounded emotional distribution prior in the VAD space by combining the lexical prior of the annotated
emotion with image-specific contextual information. Based on this prior, we introduce a Distribution-Aligned Emotional Diversity Reward (DEDR), which measures the leave-one-out marginal contribution of each candidate
emotion within a rollout. DEDR rewards candidates whose inclusion brings the predicted affective set closer to the context-grounded prior, thereby preserving plausible subjective interpretations without encouraging unconstrained dispersion. We further develop Counterfactual Visual Intervention Gating (CVIG), which masks the visual region highlighted in the
reasoning process and uses the resulting candidate-wise probability changes to reduce the weights of interpretations unsupported by visual evidence. Extensive experiments demonstrate that DSPO achieves state-of-the-art performance across multiple public
benchmarks, especially on the cross-domain performance, i.e., improving +10.8% on average cross-domain accuracy than EMO-R3.
Read the full abstract ▾
All authors Cheng Ye, Weidong Chen, Bingyan Xu, Zhendong Mao
Robotics
LexiconVLA: Learning Reusable Atomic Action Codebooks for Unseen Tasks
Zeming Wei, Jianheng Ye, Xinshuai Song et al. (+3 more)
Vision-
language-action (VLA) models struggle to reuse recurring interactions in unseen tasks. Our diagnostic study reveals that reliable task completion does not imply consistent execution of constituent atomic actions across task contexts. We present LexiconVLA, a retrievable atomic-action lexicon for cross-task reuse. Global and detail codebooks capture shared interaction structure and fine-grained execution variation, respectively, preserving both reusable patterns and execution details. Visual-Atomic Action
Alignment couples trajectory reconstruction from visual state changes with visual outcome prediction from action codes, grounding the lexicon in motion and its effects. We learn these codebooks with trajectory reconstruction and visual
alignment on our AtomAction
Dataset of 57,803 segments from 69 tasks. A planner and scene-aware adapter translate new goals into code-conditioned subtasks for a shared policy, without skill-specific experts or deployment-time parameter updates. Across five policy backbones on 26 RLBench tasks, LexiconVLA largely maintains performance on 18 seen tasks while improving success on 8 tasks held out from policy training. With BridgeVLA, unseen-task success rises from 16.67% to 34.17% (+17.50 percentage points), and overall success reaches 71.08%, the highest among methods with reported results. Real-
robot experiments demonstrate stepwise execution and failure recovery.
Read the full abstract ▾
All authors Zeming Wei, Jianheng Ye, Xinshuai Song, Sirui Chen, Yang Liu, Liang Lin
Neural and Evolutionary Computing
NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics
Yi Cui, Tong Zhao, Jiaxin Lei et al. (+5 more)
Clinical scalp electroencephalography (
EEG) offers a noninvasive window into neural dynamics of neuropsychiatric disorders. However, discriminative deep models often lack anatomically indexed physiological interpretability. We propose NeuroDyn-
EEG, a pretraining framework integrating generative priors from neural dynamics. It couples an extended Jansen-Rit neural mass model, leadfield-based source projection, and simulation-based parameter inversion. Trained on synthetic parameter-
EEG pairs within physiological ranges, NeuroDyn-
EEG estimates 11 regional parameter families across 90 AAL regions plus one global parameter from standard 19-channel
EEG, using only ~2.43M trainable parameters. We evaluate the framework across three levels. First, controlled simulations demonstrate robust parameter recovery under diverse noise conditions, while real resting-state
EEG evaluations confirm spectral and phase consistency in an inverse-forward closed loop. Second, on four clinical
benchmarks (AD65, PD31, Figshare MDD, and TUAB), NeuroDyn-
EEG achieves competitive classification performance, securing the highest BACC, AUROC, and AUCPR on PD31 and MDD, and highest BACC on AD65. Third, post hoc regional analyses reveal disease-specific alterations: local synaptic connectivity C_1 involves the most altered regions in AD65, whereas the firing threshold theta ranks first in MDD, offering testable mechanistic hypotheses. Overall, NeuroDyn-
EEG maps scalp
EEG to anatomically indexed dynamical parameters, bridging representation learning and mechanistic neurophysiology. Code: https://github.com/Gnosis-Neurodynamics/NeuroDyn-
EEG.
Read the full abstract ▾
All authors Yi Cui, Tong Zhao, Jiaxin Lei, Chuyi Yang, Yifan Cui, Ling Zhang, Yuxiang Yan, Bo Hong
Machine Learning
Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models
Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang et al. (+3 more)
Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anomalous observations with corresponding reference (i.e., regular) observations. However, existing approaches rely either on heuristic methods or on conditional independence tests with a strong unconfoundedness assumption, and thus fail to exploit other complicated distributional constraints in the presence of latent variables. To relax these assumptions, we model the underlying system as a causal model and the anomalous system as a change in the structural functions of the same causal model. Specifically, to handle unobserved confounders, we establish an implicit connection between distributional constraint testing and root cause analysis. To adapt our approach to data generated from arbitrary causal models, we employ the deep causal model (DCM) framework, in which we design the causal model using neural networks. Finally, we illustrate how our method, RCA-DCM, can utilize different levels of partial graphical knowledge to perform RCA. We evaluate RCA-DCM against state-of-the-art baselines on simulated
datasets, a physics-based causal chamber and two micro-service applications. RCA-DCM improves top-1 accuracy over the strongest baseline on both Sock Shop (0.880 vs. 0.752) and Online Boutique (0.776 vs. 0.712), and when the true root cause in the causal chamber is unobserved and acts as a latent confounder, it recovers the exact root-cause set more often than any competing method (perfect recovery rate (PRR) 0.846 vs. 0.731).
Read the full abstract ▾
All authors Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang, Padmaja Jonnalagedda, Ruocheng Guo, Murat Kocaoglu
Artificial Intelligence
Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients
Aram Davtyan, Pablo Acuaviva, Sebastian Stapf et al. (+1 more)
Can a population of neural networks develop a useful division of labor without a shared gate or gradients between
agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another
agent for help through a forward pass. Unlike mixtures of experts, where a jointly trained gate assigns inputs to experts, specialization here must emerge without central control. We test this in a small scale proxy for predictive visual pretraining. Initially identical
agents are finetuned on an unlabeled mixture of six visual domains using masked prediction of frozen DINOv3 features. We measure specialization by asking whether the best
agent for an input aligns with its latent domain, and utilization by asking whether responsibility is distributed across
agents. We progressively remove central control, ending with DISCO (DIStributed COllaboration) where each
agent locally selects a helper, reads its internal state through a gradient free channel, and rewards its router only for the improvement that help provides. Specialization emerges and is useful. Randomly routed populations underperform a single generalist, while semantically routed populations outperform it, showing that specialization rather than population size drives the gain. Specialization persists without a central router, and gradient free communication lets nonexperts exploit emergent expertise. In DISCO, a random
agent helped by the expert matches the solo generalist, while experts surpass it, including on data outside the specialization mixture. Local routers select the emergent expert for 98% of inputs. These effects persist across population size, model capacity, data imbalance, and finetuning seeds, providing measurable evidence for the dynamics needed by decentralized predictive pretraining.
Read the full abstract ▾
All authors Aram Davtyan, Pablo Acuaviva, Sebastian Stapf, Paolo Favaro
Machine Learning
When Can Prefixes Compile LoRA? Exact Resource-Capped Tests for Frozen Attention
Joyanta Jyoti Mondal and Ibne Farabi Shihab
Can a fixed continuous prefix replace a given low-rank adapter while the
attention head stays frozen? In this research, we show that the answer depends on the adapter's target through three conditions. First, observability: at one causal readout, every independent key–value prefix sees the content only through the query,
attention partition, and value numerator, so a target that differs on two inputs with equal summaries incurs an error floor at every prefix length; norm caps extend this floor to nearly equal summaries. Second, realizability: at a common query, any prefix reduces exactly to two aggregate variables, and the norm-capped optimum is an attained second-order-cone program, also after a fixed output projection; it places two equal-norm rank-one value updates on opposite sides of compilability. Third, implementation: under affine query exposure, $2r$ signed slots approximate a rank-$r$ value update, but their values grow as $O(\epsilon^{-3/2})$, and the construction passes all 400 tolerance checks in float64 yet only 38 in bfloat16. A first-layer GPT-2 readout with fixed
token and position meets the common-query condition without clamping activations; at three such heads, the capped optimum leaves 18.4% to 74.2% of the projected adapter effect uncompiled, with a head-dependent value–query ordering. All claims concern local approximation at one head, not whole-network equivalence.
Read the full abstract ▾
Machine Learning
Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection
Zepeng Zhang, Jhony H. Giraldo, Wenbin Wang et al. (+1 more)
Multivariate time series anomaly detection typically relies on evaluating discrepancies between observations and outputs produced by models trained on normal data. An alternative perspective is to characterize the distribution of normal data through the generative dynamics, i.e., the velocity field, of flow matching models. However, standard flow matching typically adopts linear probability paths that overlook dependencies among variables, leading to a misalignment with the structured data distribution. To address this issue, we propose GRASP, a flow matching framework with a graph-spectral path for multivariate time series anomaly detection. GRASP incorporates graph structure into the probability path by minimizing a fixed-endpoint action that combines kinetic energy with graph Dirichlet energy. This formulation yields a closed-form path based on graph-frequency-dependent
hyperbolic interpolation. A velocity predictor trained on normal data then detects anomalies using weighted velocity discrepancies aggregated across source samples, flow times, and graph frequencies. Theoretically, we establish that GRASP is invariant to the choice of
Laplacian eigenbasis and decompose its expected oracle anomaly score into bounded endpoint uncertainty and graph-frequency-weighted Fisher discrepancy. Experiments on four
benchmarks demonstrate the superior anomaly detection performance of GRASP and validate the effectiveness of its graph-spectral path and weighting mechanism.
Read the full abstract ▾
All authors Zepeng Zhang, Jhony H. Giraldo, Wenbin Wang, Olga Fink
Networking
SCORAS-MoE: Joint Compression and Resource-Adaptive Deployment of MoE-VLMs in LEO Satellite Networks
Tong Quan, Yuanlong Wan, Huasen He et al. (+4 more)
Deploying large
vision-
language models (VLMs) onboard satellites enables onboard data processing and reduces raw data downlink. However, onboard inference faces two resource challenges. Limited onboard
memory and energy require model compression and distributed deployment. Dynamic resource availability requires fast deployment decisions as illumination, battery levels, and communication conditions change. We present SCORAS-MoE, a joint compression and deployment framework for mixture-of-experts (MoE) VLMs in low Earth orbit (LEO) satellite networks. To address limited resources, SCORAS-MoE measures the perturbation of the routed MoE output caused by low-rank approximation, assigns higher ranks to more sensitive experts, and distributes compressed model shards across satellites for cooperative inference. The compressed models yield profiles of measured accuracy and inference energy. To adapt to dynamic resources, the online scheduler selects profile compositions and shard placements in each slot. For each candidate composition, it reduces placement to a minimum-cost assignment problem solved by the Hungarian
algorithm, while enumerating the compositions yields the optimal deployment for the current-slot objective. Experiments on Qwen3-VL-30B-A3B-Instruct show that allocating ranks based on output perturbation is particularly effective under aggressive compression, with an absolute gain of $3.7\%$ in mean accuracy over uniform rank allocation when expert projections retain $30\%$ of their original parameters. The fixed-profile scheduler achieves higher throughput with fewer service switches and lower battery impact than the evaluated proximal policy optimization (PPO) and evolutionary baselines, with respective speedups of $8.7\times$ and $183.5\times$. Adaptive profile selection further improves the balance between service quality and energy use.
Read the full abstract ▾
All authors Tong Quan, Yuanlong Wan, Huasen He, Yunpeng Hou, Shuangwu Chen, Xiaofeng Jiang, Jian Yang
Machine Learning
Federated Clustering with Unknown Local and Global Cluster Cardinalities
Mitushi Goyal, Tarun S., Riddhanya Senapathi et al. (+1 more)
Federated clustering methods that do not require the global number of clusters $K$ still assume that each client knows its local number $K_g$. This assumption is hard to justify when clients know no more about their data than the server does, as in fault diagnosis across independently operated industrial sites. We propose a two-phase framework in which neither count is known: each client first estimates $K_g$ from its own data, and an aggregator that requires local counts, such as FedGEM, then uses these estimates in place of the true values. For the first phase we introduce Adaptive Split–Merge (ASM), which grows a spherical Gaussian mixture by BIC-driven splitting and then merges excess components. ASM uses no labels, selects its hyperparameters on held-out client data only, and makes no assumption about how clusters are shared across clients. We derive a closed-form split criterion whose critical cluster size falls with anisotropy and rises with dimension, and show empirically that over-fragmentation grows with the number of points per cluster, which federation divides among clients. Across eight
datasets, ASM with FedGEM attains a mean ARI of 0.333, against 0.256 for the next best label-free
estimator and 0.361 when the true local counts are supplied. It also gives the most reliable global estimates of $K$ and is robust when client size is decoupled from local cardinality.
Read the full abstract ▾
All authors Mitushi Goyal, Tarun S., Riddhanya Senapathi, Arun Raman
Discrete Mathematics
The Reach of Abelian Covers in Hypergraphs
Joshua Brakensiek, Venkatesan Guruswami and Aaron Putterman
Covers in hypergraphs are frequently studied to capture various forms of dependence between hyperedges. For example, even covers–which check if each vertex appears in an even number of hyperedges–have found much success recently in the study of locally decodable codes. Inspired by a recently-emerging line of work on the non-redundancy of constraint satisfaction problems (CSPs), we introduce and study two novel families of covers of hypergraphs which are stricter than even covers: Abelian covers and Catalan covers. Abelian covers are similar to even covers, except that arithmetic is now done over the integers rather than modulo 2, allowing us to capture dependences over arbitrary Abelian groups. Catalan covers capture the behavior of non-Abelian groups by only allowing local cancellations in a sequence of hyperedges. We prove three main results about Abelian and Catalan covers. First, using tools from
lattice theory, we show that any $r$-uniform hypergraph with $n$ vertices and $n \log(r)$ hyperedges has an Abelian cover. Second, using tools from algebraic
topology, we show that in any $3$-uniform hypergraph, Abelian covers and Catalan covers are equivalent; thereby showing that Catalan covers emerge after $O(n)$ hyperedges in $3$-uniform hypergraphs. Finally, using the theory of nilpotent groups, we show that there exists a $4$-uniform hypergraph which has an Abelian cover but not a Catalan cover. Collectively, these results exactly characterize the reach that Abelian covers have in deducing dependences in hypergraphs. As our primary application, we show that any arity-$3$ CSP with an infinite-domain Mal'tsev extension has linear non-redundancy. This implies near optimal streaming, sparsification, and kernelization
algorithms for this family of CSPs. Previously, such a result was only known for the much simpler case of arity-$2$ CSPs.
Read the full abstract ▾
Machine Learning
QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
Zunhai Su, Yuxuan Sun, Jianchao Tan et al. (+5 more)
Multi-Head Latent
Attention (MLA) enables expressive multi-head
attention with compact caches for its content and decoupled RoPE paths, yet cache
memory still scales linearly with context length and batch size. In this work, we establish a systematic model of MLA's dual-path quantization errors, characterizing their distinct effects on
attention-output distortion and explaining the pronounced amplification of RoPE-path errors. Guided by this analysis, we introduce QuantMLA, a function-aligned framework for low-bit dual-path quantization. We derive path-specific transformation spaces that preserve full-precision computation while remaining fully fusible into model parameters offline, eliminating online transformation overhead. Within these spaces, QuantMLA learns path-specific transformations with function-aligned objectives:
attention-output reconstruction captures the content path's coupled matching and aggregation errors, while positional QK reconstruction preserves the RoPE-induced component of the
attention logits and admits a theoretical bound on output distortion. Across four MLA model families, QuantMLA enables, to our knowledge, the first reported joint INT4 caching of the content and RoPE caches with minimal accuracy degradation. Further compressing the content cache to INT2 while retaining the RoPE key cache at INT4 maintains competitive performance on challenging
reasoning and code
benchmarks. We develop a native low-bit MLA
attention kernel that integrates unpacking and dequantization directly into
attention computation. The physical cache layout provides 3.59x compression at 128K context, while a cache-pressure serving workload achieves 5.168x higher whole-job output throughput than BF16. The code will be released upon acceptance.
Read the full abstract ▾
All authors Zunhai Su, Yuxuan Sun, Jianchao Tan, Tao Zhang, Ruihan Hu, Yuchen Xie, Xunliang Cai, Ngai Wong
Computer Vision
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
Chiyuan He, Zihuan Qiu, Fanman Meng et al. (+5 more)
Benefiting from transferable visual-textual
alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners either repeatedly update components shared across tasks, leading to knowledge overwriting, or overly isolate new-task updates, hindering the reuse of CLIP's transferable knowledge and limiting plasticity. Moreover, the text-based or bimodal classifier designs still fail to effectively integrate complementary information from the visual and textual modalities. To address these challenges, we introduce DuLBE, which couples dual-mode low-rank learning with a bridge-prototype ensemble classifier for exemplar-free CIL. DuLBE allocates two visual low-rank update modes according to the gradient demand and uses gradient routing to coordinate them: a compact and rewritable shared mode is selected from historically occupied visual directions to reuse transferable knowledge, while residual modes provide low-interference channels for task-specific variations. Building on the resulting stable inter-modal structure, we further construct geodesic bridges between visual prototypes and text
embeddings on the unit hypersphere, and ensemble reliable bridge prototypes to compensate for the modality-gap limitations of textual decision boundaries. Extensive experiments under multiple settings show that DuLBE achieves state-of-the-art CIL performance while retaining the high parameter efficiency of low-rank tuning.
Read the full abstract ▾
All authors Chiyuan He, Zihuan Qiu, Fanman Meng, Chao Wang, Liangjiang Chen, Linfeng Xu, Qingbo Wu, Hongliang Li
Computer Vision
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Xiaoxu Chen, Qin Yang, Haoran Bai et al. (+2 more)
Diffusion-based
video restoration recovers realistic details, but its practical deployment is limited by two efficiency bottlenecks: costly VAE encoding and decoding, and the quadratic cost of full self-
attention in
diffusion transformers (DiTs). This paper presents FastVR, a streaming
video restoration framework built on a one-step
diffusion model, which delivers strong restoration quality and temporal consistency while processing 1080p
video at 11 FPS on a single H20 GPU. To improve inference efficiency, FastVR combines a lightweight VAE with chunk-wise causal
attention, which substantially reduces the computational cost. During training, it further adopts velocity consistency regularization and continuous trajectory learning, which improve restoration quality. Extensive experiments show that FastVR is more efficient than the evaluated
diffusion baselines while achieving state-of-the-art performance on synthetic and real-world
benchmarks. We hope that this work supports further progress in the community.
Read the full abstract ▾
All authors Xiaoxu Chen, Qin Yang, Haoran Bai, Sibin Deng, Ying Chen