Robotics
Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation
Yuyan Li, Yujia Wang, Yusong Huang et al. (+8 more)
Action-chunking policies predict multi-step control sequences, but a fundamental question remains: how much of a predicted action chunk should be committed before replanning? Existing systems typically execute a fixed-length prefix, implicitly assuming that the same execution horizon remains trustworthy across states. Some adaptive methods estimate this horizon from the similarity or stability of predicted actions. However, different actions may lead to the same successful outcome, whereas similar actions can produce different futures, suggesting that commitment should be determined by agreement among imagined futures rather than by similarity in action space. To this end, we propose Consequence-Aware Adaptive Action Chunking (CA$^3$C), an inference-time framework built on a simple principle: commit while imagined futures agree, and replan when they diverge. Without modifying or retraining the base policy, CA$^3$C uses an action-conditioned world model to imagine the future consequences of multiple candidate action chunks under the same sampling noise. Using these imagined consequences, we formulate execution-horizon estimation as a
Bayesian change-point inference problem and select the execution candidate through future consensus. Across multiple simulation
benchmarks and real-world
robot manipulation tasks, CA$^3$C consistently improves diverse action-chunking policies, achieving up to a 71.8% relative reduction in failure rate over the corresponding base policies.
Read the full abstract ▾
All authors Yuyan Li, Yujia Wang, Yusong Huang, Junjie Yang, Yanggang Sheng, Ziyi Shi, Wenpeng Xu, Xiaoyang Zhou, Haoang Li, Hongliang Lu, Xinhu Zheng
Artificial Intelligence
Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents
Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti et al. (+2 more)
When using an LLM
agent in a consequential domain, making an informed decision about whether to trust its output or intervene requires calibrated confidence in the
agent's success. Confidence estimation for
agents is difficult because evidence about success is distributed across heterogeneous, interdependent steps of an
agent's trajectory. Practical agentic deployments introduce further challenges: frontier LLMs often provide limited access to internal signals,
agent roll-outs are costly, and training data may be unavailable or quickly become outdated. To address these challenges, we introduce Confidence
Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an
agent accomplished its task from a single trajectory, without privileged model access or training data. Rather than compressing an execution into a single holistic judgment, a CRG begins with the claim that the
agent accomplished its task, decomposes it into contextualized sub-claims grounded in trajectory evidence, estimates confidence for each terminal claim, and finally aggregates these into an overall confidence estimate. Across three agentic
benchmarks, three backbone models, and three
agent frameworks, CRGs yield better-calibrated confidence and stronger risk-aware decision making than verbalized, sampling-based, and white-box surrogate baselines. We further find that calibration error alone can be misleading: a white-box surrogate baseline appears well calibrated while providing near-chance discrimination. Ablations attribute CRG's improvements to claim-level confidence estimation and aggregation rather than graph construction alone. Finally, a CRG exposes the claims and trajectory evidence underlying each confidence estimate, enabling it to be audited at decision time.
Read the full abstract ▾
All authors Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti, Pouya Pezeshkpour, Estevam Hruschka
Robotics
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
Ahin Lee, Jinwoo Seo, Youngsoo Jang et al. (+1 more)
Visual disruptions can arise while a
robot is executing a task, leaving a
vision-
language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous action chunk, as self-supervision for test-time adaptation. Because consecutive chunks overlap in time, the leftover provides a temporally aligned target for the current prediction over the same future control interval. At the onset of a visual shift, the leftover can retain a plan formed before the corruption, so updating the policy toward it anchors the adaptation across the shift (Transition Anchoring). SALT keeps the adapted policy and regenerates the current chunk, whose leftover becomes the target at the next replan, carrying the correction forward along the execution trajectory (Sequential Correction Propagation). Supervision comes entirely from the policy's own predictions, requiring no disruption annotations, expert actions, or target-domain demonstrations, and a lightweight adaptation gate calibrated only on nominal trajectories decides when updates begin. On LIBERO-10, SALT increases average success across five persistent visual corruptions from 43.9% to 53.2% with SmolVLA and from 58.7% to 66.0% with GR00T N1.7, while largely preserving nominal performance. On a real
robot, it raises task progress averaged over digital and physical disruptions from 0.49 to 0.61.
Read the full abstract ▾
All authors Ahin Lee, Jinwoo Seo, Youngsoo Jang, Taesik Gong
Graphics
UltraDiff: Differentiable Ray Tracing in Ultrasound for Shape Optimization
Felix Duelmer, Magdalena Wysocki, Nassir Navab et al. (+1 more)
Physically-based differentiable rendering enables gradient-based optimization of scene parameters by matching rendered images to measurements, but has so far mainly focused on light transport. We extend this paradigm to medical ultrasound, where image formation resembles transient rendering: echoes are binned by time-of-flight rather than projected onto an image plane. We present UltraDiff, a modular framework for differentiable ultrasound ray tracing. UltraDiff formulates ultrasound image formation as a path-space integral, gated by travel time between the transducer and tissue interfaces, and derives a Monte Carlo
estimator of both the forward model and its gradients with respect to scene parameters. We demonstrate this on an inverse geometry estimation: starting from a sphere, an SDF is optimized until simulated echoes match measured ones, recovering vertebral surfaces from simulated B-mode sweeps and from a real robotic acquisition of a spine phantom. Unlike state-of-the-art ultrasound shape reconstruction methods, which rely on pre-segmented images, our approach operates unsupervised on B-mode images through analysis-by-synthesis, while achieving competitive
geometric accuracy. Implemented on top of Mitsuba 3, UltraDiff brings differentiable path tracing to a new sensing modality and provides a foundation for inverse problems in acoustic imaging.
Read the full abstract ▾
All authors Felix Duelmer, Magdalena Wysocki, Nassir Navab, Mohammad Farid Azampour
Computation and Language
Yuhan Chen, Siyuan Zhang, Nan Wang et al. (+2 more)
Looped
language models apply the same stack of layers T times to each
token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent
Attention (HLA), which keeps exact keys and values within a sliding window of W recent
tokens and stores each older
token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original
attention. The cache shrinks by 10.7x per
token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-
token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and
reasoning benchmarks, and 96-100% on long-context
retrieval up to 16K
tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.
Read the full abstract ▾
All authors Yuhan Chen, Siyuan Zhang, Nan Wang, Feiyang Kang, Ruoxi Jia
Computer Vision
CCDF: A Benchmark Dataset for Deepfake Detection in Surveillance Footage
Baptiste Chopin, Thomas Swearingen, Arun Ross et al. (+2 more)
Due to rapid advances in Generative AI, commercial
video generation tools can be used to produce fabricated surveillance footage that can fool both human viewers and automated synthetic
video detectors. Since these tools are so widely accessible, a malicious user can create a harmful
video clip at minimal cost. The production and dissemination of such
videos in high-stakes settings, such as crime reporting and elections, can misdirect emergency response efforts or distort political discourse. Existing deepfake
video datasets, used by the research community to develop deepfake detection
algorithms, exhibit two limitations: (1) they emphasize benign web content rather than footage of possibly malicious activity, and (2) they rely on older or open-source generators that do not represent recent advances in generative systems. We assemble CCtv DeepFakes (CCDF), a
video deepfake
dataset, to address both gaps. CCDF contains 1840
videos (460 real and 1380 generated) spanning 16 crime and accident categories, with generated content produced using three leading commercial systems: Grok Imagine, Google VEO 3.1, and OpenAI Sora 2. CCDF is a highly realistic, small-scale, manually annotated
dataset targeting evaluation of detection models. We release three versions of the
dataset: the raw generated data, a cleaned version in which
video metadata are standardized between real and synthetic samples to prevent detectors from exploiting trivial cues, and an altered version simulating low-effort post-processing attacks. We evaluate CCDF with ten recent state-of-the-art detectors covering different detection approaches. Our results suggest that these approaches do not reliably distinguish CCDF's generated
videos from real ones, despite their strong reported performance on existing
datasets. These results further confirm the benefits of the CCDF
dataset for advancing research in DeepFake detection.
Read the full abstract ▾
All authors Baptiste Chopin, Thomas Swearingen, Arun Ross, Antitza Dantcheva, Christian Rathgeb
Machine Learning
Generalized Matheron Variational Implicit Processes
Luis A. Ortega, Andrés R. Masegosa and Thomas D. Nielsen
Implicit-process priors specify distributions over functions through sample-forward mechanisms such as
Bayesian neural networks and
stochastic simulators, but their function-space densities are typically unavailable. We introduce Generalized Matheron Variational Implicit Processes (GMVIP), a pathwise variational family for posterior inference with such priors. For Gaussian-process priors, GMVIP recovers the standard inducing-variable variational GP construction; for general implicit priors, its empirical covariance construction preserves the prior mean and covariance in the population limit. GMVIP constructs posterior samples by drawing a function from the prior and applying a correction anchored at a set of inducing inputs. The effect of this correction away from the inducing inputs is determined directly from prior samples, allowing the posterior to retain the structure and variability of the original implicit process. The (surrogate) prior and variational posterior use the same pathwise construction and differ only in the distribution of whitened inducing coefficients, yielding a tractable coefficient-space Kullback-Leibler divergence. Experiments on regression, classification, and
forecasting with simulator-defined and
retrieval-conditioned empirical trajectory priors show that GMVIP is broadly competitive with existing methods.
Read the full abstract ▾
Computation and Language
Leveraging a four-quadrant approach for evaluating Redpine Science
Filip Dorm and Leonora Vesterbacka
Redpine Science gives models and
agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Protocol (MCP) and an API. This report evaluates Redpine Science on two levels: the relevance of the retrieved chunks, and a model's answer when it has access to Redpine Science compared to web search. Both public and expert-validated
benchmarks are used. Public
benchmarks are a widely accepted way to test model development and are comparable across labs, but risk saturation and memorization. To address this, we complement them with an expert-validated question set. In total, this report presents four evaluations. On ScholarQABench SciFact, the public answer-quality
benchmark reported here, an
agent with Redpine Science answers 94.4% of claims correctly against 87.6% with no
retrieval. On the expert-validated question set, an
agent with Redpine Science states 80.1% of the required claims against 70.2% for an
agent restricted to web search. On the 668 queries of a public
retrieval benchmark whose gold paper Redpine holds, stripped of any model
reasoning, Redpine Science places the correct source paper in its top ten results for 83.1% of queries (Recall@10), against 79.3% for the
benchmark's creator. A blinded expert relevance panel places Redpine Science's Precision@5 at 75.2% against 39.8% for the PubMed search tool. We release the expert-validated question set and instructions to reproduce every headline result above, at https://github.com/redpine-ai/
benchmarks.
Read the full abstract ▾
Computation and Language
Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing
Jing Chen, Giulia Loca, Simona Amenta et al. (+1 more)
Systematicity, the probabilistic mapping of form to meaning, permeates
language at all levels, and sublexical cues have been shown to govern human pseudoword processing. Yet whether LLMs exhibit comparable sensitivity to these cues remains unclear. We tested five LLMs on two Italian two-alternative forced-choice pseudoword experiments and compared their responses with a human behavioural baseline. LLMs aligned more reliably with humans when real-word options provided a lexical familiarity cue than in the pseudoword-only condition, where they fell substantially below fastText, a character-n-gram model. In addition, the sublexical cosine-similarity cue that reliably drove human–fastText agreement did not consistently transfer to human–LLM
alignment, and
reasoning-
token expenditure bore no consistent relation to human processing difficulty. These findings suggest that LLMs do not necessarily share the sublexical cues that govern human pseudoword processing; we discuss tokenization and training-data coverage as candidate explanations.
Read the full abstract ▾
All authors Jing Chen, Giulia Loca, Simona Amenta, Marco Marelli
Artificial Intelligence
SIGMA: Self-Improving Alignment Generalization from a Model Spec
Jingyu Zhang, Shruti Palaskar, Daniel Khashabi et al. (+3 more)
LLM
agents are increasingly capable of executing complex tasks and of recursively improving themselves on easy-to-verify objectives such as software engineering and mathematics. Since
alignment is much harder to verify, this creates a growing risk of capabilities increasing without appropriate safety
alignment, especially as capabilities expand to auto-research and cybersecurity. Existing approaches focus on capability self-improvement using verifiable feedback or on
alignment training with supervision from stronger models or curated data, creating an external supervision bottleneck for
alignment. We ask whether current models can improve their own safety
alignment, and propose SIGMA, a data generation and training pipeline enabling
alignment self-improvement that generalizes to out-of-distribution settings. Given only a "Model Spec" stating the model's desired behavior, SIGMA leverages a model's
reasoning capabilities to strengthen its own safety
reasoning. SIGMA first performs spec-guided task synthesis, using the candidate model as a task designer
agent to generate diverse
alignment dilemma scenarios and convert them into training tasks that stress-test its understanding of the Model Spec. Next, SIGMA conducts self-judged
alignment training through supervised fine-tuning and rubric-based reinforcement learning with the model itself as the reward model. Despite training only on single-turn chat data, SIGMA improves safety
alignment in multi-turn agentic environments (AgentHarm harmfulness decreases from 22.6 to 14.8; Agentic Misalignment decreases from 79.1 to 3.8), outperforms Deliberative
Alignment and Constitutional AI baselines, and retains general capability. Analyses show that a Model Spec balancing harmlessness and helpfulness, test-time
reasoning for safety deliberation, and high-quality rubrics from SIGMA's task designer
agent are crucial for effective self-improvement.
Read the full abstract ▾
All authors Jingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme, Leon A. Gatys, Joseph Yitan Cheng
Cryptography and Security
Where does a rust speedup come from? Language and algorithm effects in sliding window threat scorer
Nikolaos D. Tantaroudas, Ilias Karachalios and Andrew J. McCracken
Rewriting a hot path from Python into Rust is a common way to speed up security analytics, and large speedups are routinely reported. A rewrite usually changes the
language and the
algorithm at once, so a single factor can credit the
language with a gain that comes from a better
algorithm. We study this on a sliding window threat scorer modelled on the traffic light calculator of the SentinelSphere platform. Five implementations, three in Python and two in Rust, produce bit identical scores, confirmed by a shared checksum, and we time them from 100 to one million events in a bounded and a burst regime. The
language alone contributes between about 4 and 29 times. Replacing a per event rescan of the window by an incremental update contributes more than 11,000 times in the burst regime, so the end to end factor reaches about 195,000 times when the window keeps filling and levels off near 13,000 times when it does not. A power law fit to the timings reported for the original rewrite gives growth exponents of 1.85 for Python and 0.88 for Rust, the signature of an algorithmic difference. Performance claims for security tooling should therefore report the
language and
algorithm contributions separately.
Read the full abstract ▾
Computer Vision
Jinghao Xu, Zhenhua Guo, Xiaofeng Zhu et al. (+1 more)
Dynamic
multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing methods still suffer from two limitations: (i) static cross-modal
alignment strategies usually impose uniform constraints on all samples while overlooking sample-wise variations, potentially leading to unreasonable over-
alignment; and (ii) confidence- or uncertainty-aware fusion methods often fail to adequately account for feature magnitude and confidence differences across modalities. For modality pairs with significant feature magnitude differences or small confidence gaps, it might be unreliable to strictly align fusion weights according to confidence. To address these issues, we propose an
Alignment- and Calibration-driven
Multimodal Learning framework (ACML). Specifically, ACML incorporates a dynamic cross-modal triplet
alignment module, which enforces strong semantic consistency for high-confidence positive pairs while encouraging diverse representation learning between high- and low-confidence positive pairs according to their confidence gaps. Additionally, ACML introduces a difference-aware
attention calibration strategy that adaptively adjusts
attention regularization based on feature magnitude and confidence differences across modalities, thereby mitigating biases caused by unreasonable fusion constraints. Extensive experiments on multiple
multimodal benchmark datasets demonstrate that ACML consistently achieves superior performance and robustness over recent state-of-the-art methods.
Read the full abstract ▾
All authors Jinghao Xu, Zhenhua Guo, Xiaofeng Zhu, Xiaoshuang Shi
Discrete Mathematics · Cross-listed from math.CO
Topological and Geometric Perspectives on Homomorphism Indistinguishability
Josse van Dobben de Bruyn, Jérémie Marquès, David E. Roberson et al. (+3 more)
Two graphs $G$ and $H$ are homomorphism indistinguishable over a graph class $\mathcal{F}$ if, for every graph $F \in \mathcal{F}$, the number of homomorphisms from $F$ to $G$ is equal to the number of homomorphisms from $F$ to $H$. Lovász (Acta Mathematica Academiae Scientiarum Hungarica, 1967) showed that two graphs are isomorphic if, and only if, they are homomorphism indistinguishable over all graphs. Subsequently, homomorphism indistinguishability relations of a long list of natural graph classes have been equated with natural graph isomorphism relaxations. Given the wealth of such results, Atserias, Kolaitis, & Wu (LICS 2021) asked for an axiomatic characterisation of homomorphism indistinguishability relations. By exhibiting topological and
geometric structure associated with homomorphism indistinguishability, we derive such an axiomatic characterisation. Here, a central ingredient is a novel characterisation of graph parameters of the form $\hom(F, \star)$ for some graph $F$ alternative to a previous result of Lovász & Schrijver (JCTA 2010). Moreover, we investigate the
topology of homomorphism indistinguishability and discuss repercussions for the Ulam–Kelly Reconstruction
Conjecture.
Read the full abstract ▾
All authors Josse van Dobben de Bruyn, Jérémie Marquès, David E. Roberson, Tim Seppelt, Gian Luca Spitzer, Peter Zeman
Social and Information Networks
Target-Aware Network Dismantling with Limited Budgets
Jiaqi Song, Fei Jing, Wenjie Huang et al. (+2 more)
During epidemics, limited resources dictate critical decisions about whom to isolate or monitor. Conventional public health strategies intuitively prioritize known infected individuals and their immediate contacts. Here, we reveal that this contact-centric approach is fundamentally suboptimal under realistic resource constraints. By formulating this challenge as target-aware network dismantling, we uncover a counter-intuitive, budget-dependent intervention transition. Generating-function analysis demonstrates that when intervention budgets are scarce, isolating structurally central individuals, rather than the immediate neighbours of the infected, protects a vastly larger population. The conventional neighbour-targeting strategy only becomes optimal as available resources increase. Because this critical transition point shifts dynamically with the intervention budget, network
topology, and spatial distribution of infections, static strategies inevitably fail. To overcome this, we develop Risk-Aware Isolation Learning (RAIL), a deep reinforcement learning framework that adaptively selects optimal interventions based on the evolving residual network. Across diverse synthetic and real-world networks, RAIL consistently maximizes population protection and suppresses outbreak spread. Ultimately, our findings challenge prevailing epidemiological intuitions, establishing a generalizable framework for adaptive interventions against localized risks in public health and other complex systems.
Read the full abstract ▾
All authors Jiaqi Song, Fei Jing, Wenjie Huang, Xingqin Qi, Qingpeng Zhang
Computer Vision
TF-PRVR: Training-Free Partially Relevant Video Retrieval
Giyeol Kim and Chanho Eom
Partially Relevant
Video Retrieval (PRVR) aims to retrieve untrimmed
videos containing moments relevant to a given text query. Despite recent progress, existing PRVR methods suffer from two key limitations: a fixed
video decomposition scheme that causes semantic dilution, and source-domain overfitting induced by task-specific training. In this paper, we propose TF-PRVR, the first training-free framework for PRVR. TF-PRVR leverages frozen
vision-
language features to construct
video-specific hierarchical representations. It derives temporal semantic signals from frame-level features and applies frequency-based multi-scale analysis to identify adaptive temporal boundaries, producing hierarchical segments with coherent event-level semantics. Built on these segments, TF-PRVR constructs a unified multi-scale graph and propagates query relevance across temporally and semantically related nodes. A moment-aware scoring strategy then aggregates temporally aligned relevance across scales, emphasizing consistently supported moments while suppressing isolated false responses. Without task-specific training, TF-PRVR preserves the general-purpose
alignment capability of pre-trained
vision-
language models and avoids
dataset-specific overfitting. Extensive experiments demonstrate consistent performance across
datasets with diverse visual and temporal characteristics, suggesting a practical direction for training-free PRVR.
Read the full abstract ▾
Robotics
OpenWAM: An Open Framework for Composable World-Action Models
Heng Yu, David D. Yuan, Juze Zhang et al. (+7 more)
World-action models (WAMs) couple future prediction with
robot control, yet existing systems often vary the
video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built around a common causal
robot-
video foundation and configurable
video-action interaction. Starting from Wan2.2-5B, we perform causal
robot-
video pretraining on over 10,000 hours of
video, then integrate an action expert through a shared Mixture-of-
Transformers architecture that supports joint,
video-then-action, action-then-
video, and decoupled generation. OPENWAM achieves high success rates on four LIBERO suites and real-world bimanual tasks;
robot-
video training with causal adaptation improves VTA success on LIBERO-Long from 68.4% to 97.8%. The same configurable architecture naturally extends to inverse and forward dynamics, allowing us to study how counterfactual transitions improve independently trained dynamics models beyond demonstrations alone. When only the
video predictor is adapted to a new task, a frozen local-context inverse dynamics model trained on counterfactual data and demonstrations achieves 84.0% mean success across four held-out LIBERO-90 tasks, compared with 47.0% for a full-context inverse model and 21.5% for a local-context model trained only on demonstrations. For forward dynamics, counterfactual supervision reduces RGB prediction error by 34.5% and raises outcome identification from 21.1% to 71.3% among 16 same-state outcomes. OPENWAM provides a common testbed for comparing WAM interaction designs and for studying dynamics learning from
video data beyond successful demonstrations.
Read the full abstract ▾
All authors Heng Yu, David D. Yuan, Juze Zhang, Changan Chen, Yao Feng, Michelle Baldonado, Steve Cousins, Li Fei-Fei, Jiajun Wu, Ehsan Adeli
Systems and Control
Estimating Closed-Loop Multiple-Input Single-Output Dynamic Systems using Gaussian Processes
Erik-Anant Stedjan Narayan, Sigurd Hofsmo Jakobsen and Kjetil Obstfelder Uhlen
This paper extends complex Gaussian process regression-based transfer function (TF) estimation from the single-input single-output setting to closed-loop multiple-input single-output (MISO) systems. Accurate estimation of individual TFs in closed-loop MISO systems is challenging as feedback and correlation between measured signals can obscure the contributions of each input. We formulate a Gaussian process-based
estimator for MISO systems, provide analytical conditions under which each system module can be separately identified, and show that the
estimator converges to the true TFs in the zero noise limit. Moreover, we demonstrate how conventional closed-loop bias handling techniques relying on external excitation can be employed to construct appropriate regressors. Monte Carlo simulations support the analytical identifiability results and highlight the trade-off between closed-loop bias and error introduced by constructing exogenous regressors partly from endogenous signals. The presented work offers an expressive, nonparametric alternative to existing estimation approaches for MISO systems, while providing a probabilistic characterization of the estimation uncertainty.
Read the full abstract ▾
Robotics
PACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for Execution
Yenan Chen, Junjie Shi, Lu Chen et al. (+2 more)
Demonstration-conditioned policies provide a natural interface for specifying
robot behavior, yet long-horizon manipulation remains difficult when visually similar states recur across different stages or when demonstrations and executions proceed at different speeds. We identify the resulting failure mode as stage confusion and introduce Progress-Aligned Context for Execution (PACE), a stateful method that continually reinterprets a complete demonstration according to realized execution progress. PACE compresses the demonstration into ordered
multimodal prompt tokens and uses training-only dual-edge
attention supervision to expose its latent stage structure. During execution, an episode-local fast-weight
memory causally encodes realized action-observation transitions and modulates
prompt cross-
attention, producing a progress-aligned context for a unified
diffusion action expert without test-time stage labels or stage-specific policies. PACE improves success from 88.9% to 94.0% on LIBERO-Gen Goal Chain, from 79.1% to 83.3% on Spatial Combination, and from 33.3% to 73.3% on the two-step Block Routing tasks. Failure analysis further indicates that structured demonstration
alignment and causal execution
memory jointly mitigate stage confusion.
Read the full abstract ▾
All authors Yenan Chen, Junjie Shi, Lu Chen, Zhongxiang Zhou, Rong Xiong
Computer Vision
Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
Xuekang Zhu, Kaiwen Feng, Ruifeng Wang et al. (+10 more)
Image Manipulation Localization (IML) is commonly formulated as a fully supervised learning task that estimates the optimal manipulation mask $y$ for a given image $x$. In this work, we first reveal the latent nature of artifacts and thus reinterpret IML as a latent-variable problem, $P(y|x)=\int P(y|z)\,P(z|x)\,dz$, where $z$ denotes the artifacts. Following this interpretation, we pinpoint the cause for the current IML models' insufficiency as their implicit artifacts modeling strategy, highlighting the necessity of modeling $z$ in an explicit manner. Without direct labels, feature disentanglement is the most appropriate solution for this explicit modeling. Accordingly, we propose a two-stage learning paradigm with the Pairwise Artifacts Learning (PAL) and Standard Localization (SL) phases to estimate $P(z|x)$ and $P(y|z)$ via edit relations. To support our edit-relation-based learning, we further curate EditGroup-45K, a source-anchored
dataset organized into edit groups for pair construction. Extensive experiments show that our PAL paradigm yields consistent improvements across diverse IML architectures, and empirical analyses further verify that PAL does capture artifacts explicitly through feature disentanglement. Code and
dataset are available at https://github.com/venus-guangjian/PAL
Read the full abstract ▾
All authors Xuekang Zhu, Kaiwen Feng, Ruifeng Wang, Xiwen Wang, Xiaochen Ma, Bo Du, Changjiang Jiang, Chenfan Qu, Songyu Ye, Xia Du, Wentao Feng, Jian Liu, Ji-Zhe Zhou
Computer Vision
Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images
Shrihari Dumbre and Bikash Santra
Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whole-slide images (WSIs) is essential for effective treatment planning. While
multimodal approaches that integrate pathology report text with WSIs can improve classification, existing methods often depend on computationally expensive
transformer architectures and large
language models. We propose a
multimodal knowledge
distillation (MKD) framework that combines a pretrained WSI image encoder and a clinical text encoder using Low-Rank
Multimodal Fusion (LMF) to efficiently model cross-modal interactions during training. Each WSI is represented as a bag of patches paired with a slide-level diagnostic caption. The teacher model learns fused image-text representations for subtype classification, while the student model distills this knowledge to enable accurate image-only inference. We evaluate our method on the PatchGastric
benchmark dataset and achieve at least 3.35% higher mean accuracy than state-of-the-art approaches, without relying on
transformer-based fusion, multi-task learning, or large
language models. The source code is available at https://github.com/helomelo1/MKD-LMF.
Read the full abstract ▾
Computer Vision
Diverse Motion Customization via Control-based Dynamic Optimization
Youngyoon Choi, Kihyun Kim, Jeongwoo Shin et al. (+1 more)
Despite recent advances in
video generation, motion customization remains challenging due to content leakage, where appearance attributes from the reference
video unintentionally propagate into the generated output. We identify this issue as a consequence of the generative process collapsing toward the reference
video, which arises from formulating the learning objective as a direct regression on the reference. To address this, we propose Control-based Motion Customization (CMC), a principled training framework that is structurally robust to content leakage. Our key idea is to steer generative dynamics toward desired motion while avoiding collapse toward the reference
video, which we formalize using
Stochastic Optimal Control (SOC). Under this formulation, customized
videos acquire the target motion yet remain within the pre-trained model's
prompt-conditional distribution, where appearance is determined by the text
prompt rather than the reference
video. Furthermore, to improve efficiency, we tailor the SOC formulation to motion customization by eliminating the need for an explicit reward and introducing a timestep-adaptive motion cost that focuses only on early generative stages, accelerating training by 2.5 times. Extensive experiments demonstrate that CMC effectively mitigates content leakage and achieves competitive motion fidelity while preserving the diversity of the base model across diverse scenarios.
Read the full abstract ▾
All authors Youngyoon Choi, Kihyun Kim, Jeongwoo Shin, Joonseok Lee
Machine Learning
Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning
SungJae Ahn, Jeong Woon Lee, Kyoleen Kwak et al. (+1 more)
Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical
robots. Existing architectural and penalty-based approaches seek spatial smoothness by directly reducing sensitivity to changes in state inputs, but their broad constraints can degrade task performance as stronger smoothing is pursued. Temporal regularization instead constrains action differences along observed transitions, but has been considered unable to provide the spatial smoothness needed under observation noise. We revisit this assumption by proving that the temporal penalty bounds the expected action differences between current states sharing a next state, revealing a spatial effect that empirically extends to spatial smoothness. Building on this finding, we propose Conditioning for Action using only Temporal Smoothness (CATS), which combines a temporal penalty with linear ramp-up. We highlight temporal regularization's ability to provide spatial smoothness while better preserving task performance than explicit spatial regularization. Through linear ramp-up, CATS allows the policy to learn rewarding behavior before progressively smoothing its actions, improving return preservation and both temporal and spatial smoothness. Experiments in both simulation and the real world show that CATS substantially reduces action oscillation without degrading task performance, with little computational overhead.
Read the full abstract ▾
All authors SungJae Ahn, Jeong Woon Lee, Kyoleen Kwak, Hyoseok Hwang
Artificial Intelligence
Continuous Memory Machines
Ciaran Regan, Kai Arulkumaran, Luke Darlow et al. (+3 more)
Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the
memory capacity or separating timescales, but lack the combination of rapid
neuron-level processing and longer-term retention found in biology. To that end, we introduce the Continuous
Memory Machine (CMM), a recurrent architecture with
matrix-valued short- and long-term
memory states serving distinct functional roles. Building on the Continuous Thought Machine (CTM), the CMM's short-term
memory tracks recent neural activity, with uniquely parameterized
neuron-level models learning to use these activity patterns for computation. A persistent long-term
memory stores information for later use, with a
Transformer jointly updating both
memory stores, providing an expressive bidirectional read–write mechanism such that each store can reorganize its own contents and both read from and write to the other. Across algorithmic, in-context learning, and recurrent
reasoning tasks, the CMM outperforms a broad suite of baselines, exhibiting stronger generalization than prior
memory-augmented networks while preserving the CTM's interpretable
attention patterns. Code is available at https://github.com/SakanaAI/continuous-
memory-machines.
Read the full abstract ▾
All authors Ciaran Regan, Kai Arulkumaran, Luke Darlow, Stefania Druga, Sebastian Risi, Llion Jones
Artificial Intelligence
Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations
K. P. Santoso, N. Z. Fadil, F. P. Harsanti et al. (+2 more)
We study sequential content sufficiency by investigating whether a representation retains the ordered target information available in its input. An information-theoretic decomposition separates input ambiguity, representation loss, and readout mismatch. We construct recoverable views where perfect agreement and joint isotropic Gaussianity coexist with zero target information, and establish limits imposed by deterministic canonical anchors.
Token log-loss provides a one-sided information-loss bound; a fixed-penalty ridge analysis shows why rank alone cannot determine prediction risk. These results motivate CANOPE, a nonautoregressive framework with ordered latent canvases, canonical-
token supervision, and
geometric regularization. On 40,000 validation sequences, latent-agreement (PL0) and
token-grounded (PL2) have nearly identical pooled ranks but reach 13.5% and 98.8% positional Recall@1, respectively, under strong natural corruption when the correct target length is provided. On 3,930 LJSpeech validation utterances, frozen PL2 with a trained MatchaTTS readout yields 21.54% word error rate (WER) on corrupted text, versus 99.22% for frozen PL0, while end-to-end MatchaTTS reaches 10.93%. These results show that
geometric regularity alone does not guarantee recoverable sequential content or effective downstream access in the text settings studied here.
Read the full abstract ▾
All authors K. P. Santoso, N. Z. Fadil, F. P. Harsanti, R. V. H. Ginardi, G. N. Iyer
Machine Learning
ApexQuant: Data-Free Elastic Quantization by Residual Re-Isotropization
Aksel Fristrup, Sumit Pandey and Ankit Kariryaa
We introduce ApexQuant, a calibration-free quantization method that recursively re-quantizes the residual error, serving as a refinement layer on top of existing quantizers. We establish that a fresh random rotation returns each residual to the uniform distribution on the hypersphere, which characterizes the rate of progressive error decay across successive passes. This result lets us determine, before any weight is read, how many passes a layer needs for a target weight-space error. Every prefix is itself a valid lower-rate model, so one artifact serves several precisions. We instantiate ApexQuant with three interchangeable stages, scalar, $E_8$ and trellis, and validate it on four open-weight LLMs and on Earth-observation and medical domains where in-distribution data is often unattainable as imagery arrives under restrictive licences or due to patient material under
privacy constraints. Progressive re-isotropization comes within a few percent of full precision at four bits and gives the best two-bit arm we measure, in a completely data-free setting.
Read the full abstract ▾
Computer Vision
Unsupervised Long-Tailed Adaptation of Vision-Language Models
Keliang Chen, Yaxin Hou, Hui Liu et al. (+1 more)
Adapting
vision-
language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing methods typically assume a uniform unlabeled data distribution, and thus the resulting pseudo-label distribution is likewise uniform. However, real-world data distributions are often long-tailed. To tackle this, we formalize a new scenario termed Unsupervised Long-Tailed Adaptation (ULTA). Under this scenario, existing methods exhibit a contrasting phenomenon: head-class performance drops sharply, which is distinct from supervised long-tailed learning where tail classes suffer the most. In particular, we uncover that the distributional mismatch not only erodes head-class boundaries, but also pushes head samples into confusable classes, reinforcing the model's inherent bias. To address these issues, we propose a novel model called Margin-Aware Refinement with Structural
alignment (MARS). Specifically, we mitigate head-class boundary erosion via Boundary-Preserving
Alignment, which takes the zero-shot VLM as a fixed visual reference to suppress probability increases that lack visual support in the training targets. Building upon this, we introduce Margin-aware Self-Refinement, which employs a dynamic adjustment strategy to refine tail and confusable classes while preventing prediction bias. Extensive experiments on nine
benchmark datasets demonstrate that MARS outperforms state-of-the-art methods, achieving an average accuracy improvement of 4.71 percentage points.
Read the full abstract ▾
All authors Keliang Chen, Yaxin Hou, Hui Liu, Yuheng Jia
Computation and Language
ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring
Shengyu Li, Jinting Wang and Li Liu
Cantonese lyric writing requires close
alignment between lexical tones and melodic pitch. Existing melody-guided lyric generation methods typically rely on symbolic melody to generate lyrics. However, in real songwriting scenarios, melodies are often expressed as raw singing audio or hummed recordings, where pitch is implicit, noisy, and unstructured, making these methods difficult to apply directly. To address this limitation, we propose ARIA, a two-stage audio-driven melody-tone relation modeling framework for Cantonese lyric authoring that generates Cantonese lyrics from singing recordings with provided character-level timestamps. Specifically, we first design a Tri-Stream Relation-Aware Tone
Estimator (TRATE) to predict 0243 sequences from timestamped singing audio by modeling multi-stream acoustic cues and relational tonal structure. We then propose a Decoupled
Retrieval-Augmented Tone-Conditioned Lyric Generator (DRA-TCLG) to generate fluent lyrics conditioned on predicted tonal plans with
retrieval-enhanced lexical guidance. Moreover, we construct a large-scale aligned audio-Jyutping-0243
dataset from real Cantonese singing recordings to support this new task. Experimental results demonstrate that ARIA achieves strong performance in both 0243 prediction and tone-consistent lyric generation, validating the effectiveness of the proposed framework.
Read the full abstract ▾
Networking
IEEE 802.11bx - WLAN Intelligent Networking (WIN): Toward an AI-Ready Wi-Fi 9
Francesc Wilhelmi, Katarzyna Kosek-Szott, Szymon Szott et al. (+1 more)
Wi-Fi 9 is expected to go beyond mere communication and provide new services such as sensing or computation. At this juncture, Artificial Intelligence (AI) is taking a leading role in the definition of the 802.11bx amendment, named WLAN Intelligent Networking (WIN). In this tutorial, we survey the recent progress made toward Wi-Fi 9 within IEEE 802.11 standardization, tracing the drivers and technological advances that motivate an AI-ready Wi-Fi 9. We then examine AI's role along three complementary dimensions, i.e., AI as a protocol (AI is applied to Wi-Fi's PHY/MAC operation), AI as a platform (Wi-Fi infrastructure is repurposed to provide AI computation), and AI as traffic (AI flows call for new traffic-handling policies), and discuss candidate features and open challenges along each. As a concrete illustration of the AI as traffic paradigm, we present a case study on AI traffic differentiation, where we explore a potential extension of the current Enhanced Distributed Channel Access (EDCA) to support new AI traffic flows.
Read the full abstract ▾
All authors Francesc Wilhelmi, Katarzyna Kosek-Szott, Szymon Szott, Boris Bellalta
Machine Learning
Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
Guhyeon Kang and Minhae Kwon
Generative actors are transforming offline reinforcement learning (RL) by enabling expressive policy classes that model complex action distributions. However, this expressiveness also exposes a key challenge in heterogeneous
datasets: generative policies can reproduce unreliable action modes whose return distributions exhibit high variance, occasionally yielding high returns by chance but lacking consistency. Consequently, maximizing the expected $Q$-value alone is insufficient for identifying reliable actions. We propose VAN-Flow (Variance-Averse $n$-step Flow), a framework that promotes reliable actions in generative offline RL. VAN-Flow combines (i) a categorical distributional critic, (ii) a variance-averse expectation operator that smoothly reweights atom probabilities to favor actions with both high returns and low dispersion, and (iii) a flow-matching generative actor guided via rejection sampling. Unlike CVaR or mean-variance objectives, the operator redistributes probability mass over the categorical return distribution without hard truncation or auxiliary penalty terms. Across more than 40 tasks from D4RL and OGBench, VAN-Flow consistently outperforms strong baselines, with the largest gains in long-horizon and high-variance regimes where reliable action selection becomes critical.
Read the full abstract ▾
Machine Learning
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Jia Liufu, Bin Hu, Linglin Jing et al. (+5 more)
Repository-level software engineering (SWE) is a challenging long-horizon setting:
agents must reason over extended interactions, use tools, and adapt to stateful environments. Recent work trains SWE
agents with reinforcement learning methods such as Group Relative Policy Optimization (GRPO), which independently sample multiple trajectories per issue, test the resulting patches, and compare terminal rewards within a fixed group. However, this training setup does not reuse verifier feedback from failed patches as context for subsequent attempts, even though this feedback contains valuable diagnostic information about what went wrong. Training on recovery trajectories is challenging because the preceding outcome determines whether the next trajectory is generated, while the failed execution determines its conditioning context. We introduce FC-SWE, a failure-conditioned RL framework that incorporates recovery attempts into policy training. After a patch fails verification, FC-SWE restores the repository to its original task state and uses the failed patch and verifier feedback as context for a recovery trajectory. FC-SWE adapts GRPO to these chains of complete, multi-turn tool-use trajectories through two mechanisms. Trajectory-local rewards preserve each attempt's verifier outcome, preventing recovery success from rewarding an earlier failed patch. Active-set advantage estimation forms a comparison group from all initial and recovery trajectories actually executed for the same issue, so failed attempts remain in the group while unexecuted attempts are excluded. On all 500 SWE-bench Verified tasks under a verifier-assisted protocol, FC-SWE with Qwen3.5-4B and SWE-
agent achieves 41.7% Resolved@1 and 52.8% Resolved@2, compared with 38.9% and 48.5% for GRPO. Although trained with at most two attempts per chain, FC-SWE reaches 70.7% Resolved@11 under an eleven-attempt test-time budget.
Read the full abstract ▾
All authors Jia Liufu, Bin Hu, Linglin Jing, Terry Kong, Yuki Huang, Ashwath Aithal, Wenming Yang, Jun Yang