Computer Vision
H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression
Or Ronai, Vladimir Kulikov and Tomer Michaeli
Training-free
diffusion-based compression methods repurpose the generative priors of a
diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaussian codebooks remains costly in both
memory and computation, and scales poorly with the large latent dimensions of modern image and
video generators. Their combinatorial bitstream encoding further becomes computationally heavy at this scale. We introduce H-DDCM, a scalable generative compression framework that replaces Gaussian codebooks with implicit randomized Hadamard dictionaries. The fast Walsh-Hadamard transform allows for implicitly synthesizing full-dimensional dictionaries with $O(d \log d)$ compute for projection and reconstruction and $O(d)$
memory, without materializing the full-dimensional dictionary. We further introduce an efficient table-free lexicographic coding scheme that makes combinatorial encoding practical at larger dimensions. Beyond images, we adapt the framework to an autoregressive
video flow model and develop a streaming compression scheme that periodically re-encodes recently reconstructed frames into a fresh KV-cache prefix, preserving temporal context across segments at no additional transmitted bits. This enables long-form, close to real-time generative
video compression on a single GPU. Across image and
video benchmarks, H-DDCM achieves competitive rate-distortion-perception performance while substantially reducing the
memory and computational overhead of codebook-based training-free generative compression.
Read the full abstract ▾
Robotics
MARTS: A Modular Agricultural Robot for Targeted Spraying of Diseased Tomato Plants in Greenhouses
Rajmeet Singh, Manveen Kaur, Yusuf Adamu et al. (+2 more)
Broadcast spraying remains the dominant method of disease control in greenhouse tomato production, yet it treats healthy and diseased tissue alike, exposes workers to hazardous aerosols, and depends on operator skill. This paper presents MARTS (Modular Agricultural
Robot for Targeted Spraying), a low-cost robotic platform that closes the loop from plant-level disease detection to leaf-localised spray delivery in commercial greenhouses. MARTS integrates a Clearpath Husky A200 mobile base, a UR5 manipulator, a novel modular spraying end-effector built around a single 12 V micro-diaphragm pump, and a wrist-mounted Intel RealSense D435 RGB-D camera. Disease detection reuses our previously published Tomato Leaf Disease
Vision Language Model (TLDVLM; Grounding DINO, SAM-2 and LoRA-tuned BLIP-2, 97.27% accuracy over 10 classes); this work focuses on actuation, control and system integration. A ROS pipeline lifts detections into 3D targets, generates collision-aware nozzle poses at a 120 mm stand-off using fitted leaf normals, and scales pump pulse duration to lesion area. Water-sensitive paper calibration showed a linear pulse-volume relationship (R^2 = 0.994). In MuJoCo simulation, an adaptive base-repositioning strategy achieved 100% coverage of 18 waypoints with a maximum orientation error of 1.1 deg. Deployed at the SILAL commercial greenhouse (Al Ain, UAE) on cherry tomatoes under natural infection, MARTS treated 312 diseased leaves in 12 autonomous trials with 92.4% targeting success, 18.7 mm mean spray-centre error, 6.1% adjacent-leaf overspray, and a 71% reduction in pesticide volume versus broadcast spraying. Mean cycle time was 4.8 s per leaf, and the spraying subsystem costs USD 412, 6-10x lower than comparable systems, showing that accurate leaf-level targeting is achievable on commodity hardware.
Read the full abstract ▾
All authors Rajmeet Singh, Manveen Kaur, Yusuf Adamu, Lochan Kshetrimayum, Irfan Hussain
Computation and Language
Cheap, Consistent, Calibrated, but Biased? Typed Decision Models as Judges
Fabian Lukassen, Christoph Weisser and Alexander Silbersdorff
Typed decision models (TDMs) return a probability for each allowed answer instead of generating text, which makes them candidates for cheaply replacing LLM judges that compare two answers. Whether they share the biases of LLM judges is untested. We run the CALM
benchmark's bias tests on eight TDMs and seven LLM judges of 2024 and 2026. Every TDM is biased, in three to eight of twelve tests. Emotional tone affects them most, and rewriting the better answer in such a tone lowers the accuracy of a typical TDM from 99% to 42%. TDMs are more biased than 2026 LLM judges. All eight change verdicts when the answers swap places, which the 2026 LLM judges hardly do, and several side with an answer that most people allegedly prefer or that a famous model allegedly wrote. Yet both kinds of judge are tripped up by the same
prompts. The TDMs' probabilities show that most tests mainly flip verdicts the TDM was unsure of, and that good calibration does not protect against bias. As TDMs are more consistent and 37 times cheaper than 2026 LLM judges, our results suggest they can be attractive judges if their biases are tested for the task.
Read the full abstract ▾
Computation and Language
Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering
Donghoon Jung, Min Kim, Seojin Choi et al. (+2 more)
Do
language models carry information about narrative events before writing them, and how far ahead? We examine narrative lookahead through salient, state-changing events rather than
tokens or response-level attributes. We extract 23,355 LLM-annotated events from 2,000 stories generated by four open-weight LLMs, labeling them along three nonexclusive dimensions of change: within
agents, between
agents, and in the story world, with human validation on a subset. Event segmentation and plot-independent labels enable comparisons across stories at horizons measured in events rather than in
tokens. At event ends, we probe hidden states for upcoming event types and compare predictions with text-only predictors using matched prefixes. Across four models, future event types are decodable above prevalence baselines for at least four subsequent events, but probes significantly outperform both primary text-only predictors only for the next event. In exploratory steering with OLMo-3.1-32B, a probe-derived direction shifts the proportion of the target event type in both intended directions at higher strengths. Our event-level approach links the prediction of future narrative developments to interventions that reshape subsequent event composition.
Read the full abstract ▾
All authors Donghoon Jung, Min Kim, Seojin Choi, Songeun Chae, Seohyon Jung
Logic in Computer Science
Certifying Almost-Sure Reachability in Unknown MDPs
S Akshay, Suguman Bansal and Gaurav Mahla
Specification-Guided Reinforcement Learning (RL) has largely concerned itself with learning an optimal policy against a formal specification in an unknown Markov Decision Process (MDP). We take up the dual question. Given a policy already in hand, can one verify that it is correct against a formal specification in an unknown MDP, using sampling access alone? Such a question arises naturally in safety-critical systems. We investigate it for the almost-sure reachability property, whose correctness is witnessed by a ranking supermartingale (RSM) certificate. Our first finding is negative. In the absence of any further information about the MDP, one can neither learn such a certificate nor verify a candidate one with probabilistic guarantees. On the positive side, we show that, under a mild restriction, a known lower bound $p_{\min}$ on nonzero transition probabilities, a correct certificate can be learned with PAC-style guarantees. To the best of our knowledge, this is the first study of learning and verifying certificates for almost-sure reachability in unknown MDPs from sampling access alone. Finally, our experiments show that the $p_{\min}$-based sufficient condition, while sound, is conservative: the learned certificate often remains valid on the true MDP even when the condition fails.
Read the full abstract ▾
Robotics
ForeTac: Predictive Contact Guidance for Generative Robot Policies
Zhiyuan Chen, Shuai Chen, Haoran Zhou et al. (+7 more)
Visually similar actions can produce contact loss, jamming, slippage, or irreversible damage, while tactile feedback may arrive after a critical transition. Contact-rich manipulation therefore requires generative policies to anticipate and evaluate whether candidate actions will produce desirable contact outcomes, then adjust action generation before execution. We present ForeTac, a predictive contact-guidance framework organized as a represent-predict-evaluate-guide loop. ForeTac encodes the current tactile state, predicts the tactile consequences of a candidate action sequence, and evaluates the predicted trajectory using a contact-quality objective learned from successful and failed physical interactions. At deployment, its gradient propagates through the tactile predictor to guide action generation while the pretrained model parameters remain frozen. We evaluate ForeTac on four real-
robot tasks (planar and curved-surface wiping, card swiping, and fragile-object grasping) with
diffusion and flow-matching policies. Across these tasks, ForeTac raises the average task success rate from 36.3% to 71.3% and the average contact success rate (CSR) from 20.0% to 66.3% compared with
vision-only
Diffusion Policy. Component analyses support the tactile representation and action-conditioned foresight, and show that predicted touch preserves contact-quality ordering. Project page: https://foretac.github.io/.
Read the full abstract ▾
All authors Zhiyuan Chen, Shuai Chen, Haoran Zhou, Yizhe Zhao, Kaiyuan Yang, Zhixiang Duan, Shaoqing Xu, Ran Cao, Diyun Xiang, Yangwei You
Machine Learning
When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Enrico Chialà, Francesco Ferrini, Antonio Longa et al. (+4 more)
Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications. By leveraging the dependence between node features and graph structure, existing graph-specific methods handle missingness by propagating observed feature values along graph edges. However, these methods have mainly been evaluated in overly optimistic settings, where feature entries are removed independently and uniformly across the graph. This overlooks realistic scenarios in which missingness propagates among connected nodes, as can occur during localized sensing failures in sensor networks. We formalize this complementary notion as graph-structured mask dependence, where the joint distribution of missingness indicators is shaped by the graph, and introduce a controlled mechanism that instantiates this setting. We study propagation-based methods theoretically and empirically in this setting, showing that their effectiveness changes substantially compared with the uniformly random regime. Motivated by this limitation, we propose PEMix, designed to remain effective under challenging graph-structured missingness. Rather than propagating observed values, PEMix uses global structural representations to condition a probabilistic model of incomplete node features before message passing. Experiments under controlled graph-structured missingness and naturally occurring missingness show that PEMix remains robust across complex missingness regimes, with particularly strong performance as missingness becomes severe.
Read the full abstract ▾
All authors Enrico Chialà, Francesco Ferrini, Antonio Longa, Bruno Lepri, Filippo Maria Bianchi, Manfred Jaeger, Veronica Lachi
Machine Learning
SYNPRED: A Synergistic Approach to Multimodal Learning for Clinical Prediction
Ivana Janíčková, Yen Y. Tan, Thomas H. Helbich et al. (+6 more)
Multimodal medical data captures complementary aspects of disease. It provides a comprehensive basis for diagnosis and the identification of biological associations linked to progression or treatment response. Established contrastive learning approaches exploit shared information across modalities, but fall short in exploiting complementary, modality-specific signals relevant for a task. Here, we propose a synergistic
multimodal variational autoencoder (VAE) framework that separates task-relevant unimodal and
multimodal information from instance-specific variation task-irrelevant, allowing complementary signals across modalities to be leveraged for prediction. The method yields benefits even if modalities are missing at test time. We evaluate the method on a treatment response prediction task using medical imaging and RNA data. Empirical comparison with
alignment-based and
multimodal VAE state-of-the-art approaches demonstrates improved
multimodal prediction performance, and consistent benefits for prediction from a single modality after
multimodal training. The full code can be found here: https://github.com/cirmuw/SYNPRED.
Read the full abstract ▾
All authors Ivana Janíčková, Yen Y. Tan, Thomas H. Helbich, Philipp Seeböck, Julieta Di Marco, Zsuzsanna Bago-Horvath, Ulrike Heber, Thomas Spiegel, Georg Langs
Digital Libraries
Interpreting Paper-to-Patent Citations in AI-Related PMC Articles
Haowei Li and Yi Bu
Paper-to-patent citations connect scientific and technological documents, but their interpretability depends on how patents are used in the citing text. This study examines citation contexts and paper-level outcome associations in AI-related articles in PubMed Central (PMC). Screening 189,073 articles identified 746 with explicitly tagged patent references (0.395%), including 713 with 1,544 identifiable in-text patent-citation instances. Three large
language models classified these instances by represented content, motivation, textual position, and evaluative stance. Regression models examined associations among these dimensions, and propensity-score-matched regressions compared patent-citing papers with XML-screened controls. Background-oriented citations were predominantly neutral and introductory, whereas adoption-oriented citations were more closely associated with methodological positions and supportive evaluations. These patterns suggest heuristic configurations of contextualization, operationalization, and problematization, although classification overlap and exclusion of rare categories limit their interpretation. In matched samples, the patent-citing indicator was associated with lower scholarly-citation measures and more citations received from patents. These associations are observational, not causal. Together, these findings show that paper-to-patent citations encode heterogeneous forms of engagement with patented technology and should be interpreted as selective bibliographic signals rather than direct indicators of technology-to-science knowledge transfer or research value.
Read the full abstract ▾
Machine Learning
A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge
Cesare Barbera, Luca Stradiotti, Lorenzo Cascioli et al. (+6 more)
Large
language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too costly. Unfortunately, LLM judgments can exhibit systematic biases. Prior work has documented position, verbosity or model family of the candidate answers influencing the judge decision rather than their quality, while additional biases may remain undocumented. $\textit{Multicalibration}$ provides a natural framework to address this problem: each bias corresponds to miscalibration on an identifiable group, $\textit{e.g.}$, family bias manifests as overconfidence in answers generated by models belonging to the same family of the judge. The challenge is to fix miscalibration simultaneously across many, potentially unknown groups. To this end, we introduce $\mathrm{CaLLM}$, a post hoc framework that multicalibrates an LLM judge, thereby bounding all such biases simultaneously. We prove that $\mathrm{CaLLM}$ bounds the bias of every group whose error structure is captured by an available representation, and that augmenting it with explicit bias groups further reduces the residual bias. We then derive theoretical conditions under which $\mathrm{CaLLM}$ improves the judge's accuracy, rather than trading it for calibration. Finally, we evaluate $\mathrm{CaLLM}$ across pairwise preference
benchmarks, showing that it reduces the multicalibration error on both specified and unspecified bias groups, while improving predictive performance of the judge.
Read the full abstract ▾
All authors Cesare Barbera, Luca Stradiotti, Lorenzo Cascioli, Lorenzo Perini, Niek Tax, Daniel Haimovich, Jesse Davis, Andrea Passerini, Andrea Pugnana
Artificial Intelligence
Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Lennart Bürger, Piotr Komorowski, Moritz Weckbecker et al. (+4 more)
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the lack of a successful organizing principle that leads to generalizable conclusions about monitoring reliability in different regimes. Recent work attributes monitoring failures to the CoT not being necessary for the answer, and argues that CoT becomes monitorable when it is necessary. We show that this binary necessary/not-necessary organizing principle is too coarse by demonstrating that monitoring failures persist even if the CoT is necessary for the answer. In response, we introduce a more fine-grained organizing principle based on a hierarchy of four CoT necessity levels. Building on this hierarchy, we develop a framework for measuring CoT monitorability at the three lowest levels via intervention experiments. We demonstrate monitoring failures at all three of these levels on realistic, hard prediction tasks. On a difficult medical-diagnosis task, patient sex and a clinical attribute influence the answer in at least 19% and 24% of correct responses with a necessary CoT, respectively, yet their influence is almost never articulated. These results show that even when CoT is necessary, it is not guaranteed to be monitorable.
Read the full abstract ▾
All authors Lennart Bürger, Piotr Komorowski, Moritz Weckbecker, Evgenii Kortukov, Aakriti Jain, Sebastian Lapuschkin, Wojciech Samek
Machine Learning
The Effect of Layer Ordering in Hybrid Architectures
John Cooper, Mingchen Ma, Jiaqi Mo et al. (+4 more)
Hybrid
attention is rapidly becoming the dominant architectural choice for frontier models. Despite their successes, such architectures complicate model design by introducing additional choices, including the types and locations of layers. This combinatorially large design space has been studied empirically, but given the vast expense of training and evaluating models with different configurations, a principled understanding of the effects of layer selection and ordering is needed. We provide the first such analysis, showing that the dominant hybrid architecture is highly task-specific. Concretely, for any layer configuration, we prove that there exists a task where we can construct a model with this configuration that provably outperforms any other model of any different configuration under fixed resource constraints. Empirically, we observe that for standard training, learned hybrid architectures exhibit separations between layer orderings that match our theoretical findings. For instance, under the same
memory budget, the optimal architecture predicted by our theory for a segmented
retrieval task consistently achieves perfect accuracy, whereas the next strongest plateaus below 0.5. These results extend to deeper models, where “containing” the dominant architecture for a task indicates whether the model attains high performance. In addition, we investigate the mechanisms learned by hybrids, observing that
Transformer layers contribute the largest share of performance on associative recall across architectures. This work establishes insights into task-dependent hybrid architecture design relevant to the training and scaling of frontier-scale hybrids.
Read the full abstract ▾
All authors John Cooper, Mingchen Ma, Jiaqi Mo, Shengqi Qiu, Nathaniel Bastian, Ilias Diakonikolas, Frederic Sala
Machine Learning
From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits
Ibne Farabi Shihab and Joyanta Jyoti Mondal
Deleting singular components offers a precise way to remove a capability from a
language model, yet the first-order spectral saliency used to rank components predicts only a local loss change, whereas deletion is a finite intervention. In this paper, we study how prediction error affects selective editing, where selective editing requires degradation of a target task while preserving others. We decompose the error into derivative transfer across item splits and nonlinear response along the deletion path. We establish that outer interval screening retains every feasible candidate when every candidate's intervals contain its finite validation loss changes on every task. We evaluate these effects using one answer-only negative log-likelihood objective for search, validation, and test, with disjoint calibration and evaluation masks. The primary configuration targets arithmetic in Mistral-7B-Instruct-v0.3 while preserving code and question answering; extensions cover Llama-3.1-8B-Instruct and reversed target roles. In the primary study, which deletes 1024 coordinates from a support of 7168, calibrated intervals cover 968 of 1024 evaluation masks. Outer screening reaches the direct-selected edit after 25 verification checks, whereas direct verification abstains at a 32-check cap, but it rejects 4 of 74 feasible masks. All three selected edits pass validation, yet only one meets every test constraint. Interval coverage, feasible-candidate retention, and independent test preservation are therefore distinct properties and require separate assessment.
Read the full abstract ▾
Computer Vision
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
Sirui Zhang, Fangyun Wei, Dong Chen et al. (+5 more)
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profile. APT coordinates three
agents to construct evaluation sets from user requirements, diagnose model-specific strengths and failure modes, and generate reinforcement learning data with an adaptive
prompt distribution that emphasizes underperforming capabilities. By repeatedly evaluating, diagnosing, and updating the generator, APT lets the current model's behavior shape its next training tasks, forming a feedback loop inspired by recursive self-improvement. For general-purpose settings without user-specified evaluation scenarios, we further develop an evaluation harness that enables broad and diverse evaluation set generation. Experiments across multiple base models,
benchmarks, and generation architectures demonstrate that APT is model-agnostic,
benchmark-agnostic, architecture-agnostic, and fully automated.
Read the full abstract ▾
All authors Sirui Zhang, Fangyun Wei, Dong Chen, Jinjing Zhao, Yitong Wang, Yunuo Chen, Baining Guo, Zheng-Jun Zha
Artificial Intelligence
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Xinyang Liao, Lingyu Li, Kaicheng Shen et al. (+4 more)
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely targets general harms or specific companion platforms and risk categories, while relying on manually collected conversations, limiting scalable and user-grounded evaluation and mitigation. To address this, we introduce CompanionSafe, a unified evaluation-to-mitigation framework for AI companion safety. Its evaluation component, CompanionEval, provides scalable multi-turn evaluation by constructing 1,300 relationally grounded settings from diverse personas, matched companion characters, and dialogue scenarios across four turn tiers. Its mitigation component, CompanionGuard, converts
benchmark-exposed failures into turn-localized supervision for companion-specific risk detection. Our results show that even strong LLMs and existing guard models remain vulnerable to companion-specific relational harms, while both closed- and open-source models exhibit increasing safety risks as interactions become longer. Together, CompanionEval and CompanionGuard form a practical evaluation-to-mitigation loop for AI companion safety, turning relational safety failures exposed during multi-turn interaction into supervision for companion-specific guardrails.
Read the full abstract ▾
All authors Xinyang Liao, Lingyu Li, Kaicheng Shen, Yang Yao, Na Lu, Yan Teng, Xia Hu
Robotics
LynxScenes: A Large-Scale Real-World Benchmark for Outdoor Wheel-Legged Robot Perception, Navigation, Imagination and Reconstruction
Jun Tian, Hao Wu, Ruo Chen et al. (+5 more)
Wheel-legged
robots operating in outdoor spaces shared with humans require accurate perception, socially compliant navigation, future-scene
reasoning, and scene reconstruction. However, existing
datasets typically support these capabilities in isolation and rarely provide dense spatial and behavior-level supervision on real wheel-legged platforms. We introduce LynxScenes, a large-scale real-world
dataset and
benchmark collected with a LYNX M20 wheel-legged
robot. It contains approximately 100K 30-s navigation clips spanning 833.6 h and 3,294.7 km, with 3.0M annotated frames. The synchronized recordings include four fisheye cameras, dual
LiDARs, IMU, odometry, and
robot states. Annotations comprise 20.82M oriented 3D boxes across 27 categories, 13.89M road-structure annotations, and 20 navigation instructions organized into three layers and aligned with continuous future trajectories. LynxScenes supports four complementary tasks: instruction-conditioned trajectory prediction, BEV-based perception of 3D objects and road structures, future scene prediction, and multi-view scene reconstruction. For trajectory prediction, we further introduce a log-replay-based pseudo-closed-loop evaluator that measures safety, progress, and instruction compliance beyond trajectory imitation. Extensive evaluations across representative navigation, perception, world-model, and reconstruction methods reveal substantial remaining challenges in close-range outdoor
robot navigation. The
dataset and evaluation toolkit are planned for public release.
Read the full abstract ▾
All authors Jun Tian, Hao Wu, Ruo Chen, Yili Liao, Hongyi Lin, Jincheng Yu, Chao Li, Yingjie Niu
Artificial Intelligence
LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Yibo Wang, Senjie Jin, Yansong Ning et al. (+6 more)
Deep research (DR)
agents address open-ended information needs through multi-step
reasoning, long-horizon web search, and evidence synthesis. However, existing
benchmarks primarily focus on academic research or synthetic tasks, leaving DR
agents' capabilities in real-world life and professional productivity settings insufficiently evaluated. To bridge this gap, we introduce LifeSearch, a challenging
benchmark comprising 203 Chinese and English tasks derived from real-user query seeds across 7 concrete life and productivity domains. With more than 4,500 hours of human annotation, we construct over 4,000 expert-written, fine-grained rubrics, covering both report-content criteria for coverage and accuracy and concrete criteria specifying values, units, dates, and URLs. We conduct extensive experiments on 12 advanced DR
agents under a unified evaluation harness, systematically analyzing their performance patterns and failure modes. We find that even the best-performing frontier
agent, GPT-5.6 Sol, achieves a score of only 63.4%, leaving substantial room for improvement on realistic life and professional DR tasks. We select the grading configuration by comparing candidate LLM judges against human rubric labels, and a human ranking study shows strong
alignment between aggregate
benchmark scores and human judgments (Spearman's $\rho = 0.89$, Kendall's $\tau = 0.81$). LifeSearch provides a rigorous evaluation framework and foundation for advancing DR
agents toward real-world life and productivity.
Read the full abstract ▾
All authors Yibo Wang, Senjie Jin, Yansong Ning, Xinbing Liang, Haotian Luo, Jiazheng Zhang, Yuxuan He, Will Wu, Clarenceai
Networking
Developments in Building Towards the Indian SKA Regional Centre
Rohit Sharma and Yogesh Wadadekar
The SKA Regional Centre Network (SRCNet) is a
federated global network designed to archive, distribute, and process SKAO data products. This paper examines the evolving SRCNet architecture-focusing on the transition to version 0.2 (v0.2) requirements, including computation, orchestration, and multi-tiered storage-and details the strategy for establishing its proto-SRC infrastructure. We outline the prototype developments for the major and minor nodes in the context of v0.2. We describe the minor node compute and storage demands, establishing a pathway toward a fully operational Indian SKA Regional Centre (INSRC).
Read the full abstract ▾
Artificial Intelligence
AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses
Kaiyu Huang, Yiting Li, Angyang Gu et al. (+3 more)
Ambiguous or incomplete task specifications complicate both execution and clarification for
language-model
agents. Yet
agents' responses to these information gaps remain poorly characterized across models and execution harnesses. We present AM-Bench, a
benchmark built from 48 tasks adapted from Terminal-Bench 2.0 and Harness-Bench. Each task includes a fully specified reference and six variants spanning ambiguous or missing goals, context, and constraints. We evaluate every pairing of five models and four harnesses over 20,160 runs. Our results reveal distinct execution deficits: goal gaps hinder completion, context gaps increase
token use, and constraint gaps weaken compliance without necessarily preventing completion. Missingness lowers success more than ambiguity in all three domains. These effects also reshape system comparisons: advantages under complete information need not persist, and rankings depend on model $\times$ harness pairings and the evaluation criterion – completion, success, or repeat consistency. Estimates based on observed clarification requests and matched fully specified runs further suggest that clarification could recover unfinished work while leaving most constraint violations unresolved. Together, these findings motivate joint model-harness evaluation across information conditions and targeted clarification of unresolved requirements before dependent actions. To support future research on
agents under task underspecification, we provide the AM-Bench project repository at https://github.com/s4-lab-cuhksz/AM-Bench.git.
Read the full abstract ▾
All authors Kaiyu Huang, Yiting Li, Angyang Gu, Pinjia He, Minchen Yu, Qingjiang Shi
Artificial Intelligence
One-Sided Verification Under Limited Expert Review
Fan Nie, Haotian Ye, Shurui Liu et al. (+3 more)
AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a fundamental challenge as candidate generation scales beyond available review capacity. This paper studies verification under limited human effort, where rare valid solutions need to be prioritized while invalid candidates should be filtered out to reduce human workload. We adopt the one-sided verification objective that maximizes the rejection rate of invalid solutions (TNR) under a constraint on the false-rejection rate of valid ones (FNR), making human review cost an explicit term to minimize. Drawing on the intuition that verifying a specific error can be easier than discovering one, we introduce OSVerify, an algorithmic framework that decouples error proposal from error validation. The error proposer searches for errors in solutions across different granularities by hierarchical decomposition, while the validator distinguishes substantial errors from minor or hallucinated ones. Experiments on competition- and research-level
benchmarks show that OSVerify reduces the number of human reviews of invalid solutions by 46% on average compared to voting baselines under the same empirical low FNR constraint. Our post-training of the validator further improves the reduction to 57%. As high-impact real-world use cases, we apply OSVerify to identify errors in published research papers that are subsequently confirmed by the original authors and help resolve three Langlands open
conjectures that are confirmed by experts, demonstrating its utility to facilitate human-AI research collaboration.
Read the full abstract ▾
All authors Fan Nie, Haotian Ye, Shurui Liu, Zihao Wang, Stefano Ermon, James Zou
Artificial Intelligence
ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
Peng Jiang, Dongyang Li, Quanying Liu et al. (+1 more)
Autoresearch systems increasingly undertake entire research projects. In practice, scientific research requires systems to pursue multiple interdependent claims through a continuous, multi-stage workflow and revise experiments as evidence accumulates. Existing evaluations of autoresearch systems, however, typically score isolated tasks or final artifacts, leaving these process-level capabilities largely unmeasured. We therefore introduce ResearchFlow-Eval, a fine-grained framework for assessing continuous scientific execution and iteration at both the stage and claim levels. Each evaluation is grounded in a published anchor paper, from which we derive stage-specific rubrics that decompose each research stage into dimensions and separately scored rubric items. Using these rubrics, we score each research stage and examine experimental execution in detail, focusing on multi-claim completion and revisions across attempts. We apply the evaluation framework to general-purpose
agent harnesses, skill-augmented harnesses, and systems with research-specific orchestration. Across all evaluated systems, experimental execution consistently lags behind design and planning. Within execution, systems struggle to produce high-quality results and meet claim requirements, and repeated attempts rarely yield measurable improvements. Moreover, neither skill augmentation nor research-specific orchestration reliably yields higher scores. ResearchFlow-Eval thus extends autoresearch evaluation beyond isolated, single-objective runs to continuous workflows in which systems pursue multiple claims and refine their work across iterations.
Read the full abstract ▾
All authors Peng Jiang, Dongyang Li, Quanying Liu, Xiaoxuan Jia
Machine Learning
Same Function, Different Trajectory: No Standard Optimizer Is Equivariant to Transformer Reparameterization
Bum Jun Kim
We show that two
Transformers representing the same function can follow different training trajectories. For example, doubling a query
matrix and halving its key
matrix preserves the model's function but changes the gradient scales seen by the optimizer. Our theoretical analysis establishes that standard block-local first-order optimizers fail to scale updates with parameters under a shared learning rate. For AdamW, transforming the first- and second-moment estimates alone does not correct the mismatch between parameter and update scales. To make runs restarted from equivalent checkpoints follow the same trajectory, we balance
matrix pairs and transform their moment estimates together, bringing distinct but equivalent training states to the same starting point. To correct scale imbalance between paired
Transformer matrices without changing predictions, we propose
Symmetry-Aware Gradient Geometry Stabilization (SAGGS), which periodically equalizes the Frobenius norms of exact
symmetry pairs, and its damped variant, Soft SAGGS. SAGGS reduces perplexity (PPL) by $0.374\pm0.026$ at 101M parameters on WikiText-103, and Soft SAGGS reduces PPL by $0.780\pm0.040$ in a 31M modern-architecture replication, both under scale imbalance. In a 123.8M checkpoint-resume experiment, reciprocally rescaling
matrix pairs barely changes validation loss at restart but increases final PPL by $3.78\pm0.42$; hard and soft rebalancing recover to within $0.02$ PPL of the control.
Read the full abstract ▾
Artificial Intelligence
AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
Wenhao Zhou, Jiajun Song, Haitao Wang et al. (+11 more)
Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher
agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of
agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader
agent selects task-appropriate research orientations and guides ongoing investigations; conditional
memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive
evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.
Read the full abstract ▾
All authors Wenhao Zhou, Jiajun Song, Haitao Wang, Zipeng Qiu, Yingqi Peng, Ruida Xu, Jiale Li, Wenshuang Li, Shusheng Xu, Wei Dong, Hao Dai, Tongkai Yang, Yi Gao, Binhang Yuan
Machine Learning
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Xiyang Wu, Zhichao Liu, Shengxin zhang et al. (+4 more)
Long-horizon
agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can resolve. We introduce BELIEFWEAVER, a framework that combines persistent evidence across attempts with prospective
reasoning over repair directions. It maintains a relational belief state over frontiers, attempts, observations, and checkpoints. Execution evidence updates related frontier priorities across attempts and rollback, while diagnostic evidence gates execution. An implicit world model (IWM) evaluates repair hypotheses, predicts progress, and identifies relations among frontiers to guide exploration. We further distill these recurring IWM
reasoning components into a 9B student through supervised fine-tuning and on-policy
distillation (OPD). Across three terminal-based
benchmarks, BELIEFWEAVER improves aggregate final score by 5.1 percentage points over native Terminus-2 continuation, with positive trends in exploration efficiency. The distilled 9B student improves final score by 9.8 percentage points over the reported native baseline while reducing estimated teacher API cost by 54.8% relative to the matched teacher. These results show that persistent evidence and prospective
reasoning can improve recovery in long-horizon
agent tasks while substantially reducing reliance on teacher-model inference.
Read the full abstract ▾
All authors Xiyang Wu, Zhichao Liu, Shengxin zhang, Zongxia Li, Ming Li, Tianyi Zhou, Dinesh Manocha
Machine Learning
Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
Yiwen Qiu, Francesco Montagna, Shimeng Huang et al. (+1 more)
Selection bias is a difficult yet widespread problem in causal discovery, occurring whenever non-random selection processes lead to data that is not representative of the underlying populations. Due to its practical importance, related works have been proposed to address the problem under local [Versteeg et al., 2022] or interventional settings [Dai et al., 2025a], but general
algorithms for observational data remain elusive. In this paper, we focus on truncated data (hard selection), and provide a general result for Additive Noise Models (ANM). We show that score-based methods are a surprisingly suitable candidate due to a special property of the score function ($\nabla \log p(x)$): deterministic truncation preserves both the score of the joint distribution as well as the Jacobian of the score. While established score-matching
algorithms still fail in most settings, we actively leverage this observation to propose a new method for causal discovery that is robust under truncated data with ANMs. Overall, our approach offers a general, robust solution that is agnostic to external information about the selection process and still achieves comparable performance to the state-of-the-art approaches when selection is not present.
Read the full abstract ▾
All authors Yiwen Qiu, Francesco Montagna, Shimeng Huang, Francesco Locatello
Multimedia
DualAffect: Dual-Path Paralinguistic Integration for Generative Audiovisual Emotion Understanding
Yibo Wang, Jisheng Dang, Bimei Wang et al. (+8 more)
Understanding human emotion is essential for
multimodal systems that interpret both the content of an interaction and the speaker's expressive state. However, connecting paralinguistic cues to generated answers remains challenging, particularly when vocal expression diverges from visual appearance. We propose DualAffect, a dual-path architecture that integrates visually conditioned acoustic features and temporally organized acoustic
tokens into a shared
language decoder. The two pathways reuse the same acoustic encoding. The fusion pathway associates sound with visual content through visual queries, while the direct pathway compresses the valid acoustic sequence into ordered
tokens through an independent projector. This design gives the decoder access to both joint audiovisual context and acoustic evidence organized along its own timeline. Mixed-task adaptation with task-dependent output preservation supports emotion recognition and general audiovisual question answering within the same model. DualAffect achieves an average metric of 67.89 on CA-MER and accuracies of 62.88% on the EmotionTalk test set and 49.87% on Daily-Omni. Pathway interventions show that the trained decoder uses direct acoustic evidence alongside existing fusion. With model parameters and fusion inputs fixed, zeroing the direct
tokens reduces EmotionTalk validation accuracy by 9.75 percentage points and the CA-MER average metric by 2.66 points. The largest CA-MER subset effect occurs when the overall emotion agrees with audio but differs from
vision. These findings identify acoustic representation organization as a practical design axis for connecting paralinguistic perception to unified audiovisual generation. Code is available at https://github.com/YiboWang2002/DualAffect.
Read the full abstract ▾
All authors Yibo Wang, Jisheng Dang, Bimei Wang, Junhong Liu, Jiongpei Hou, Jingwen Zhao, Wenjun Ma, Hong Peng, Bin Hu, Qi Tian, Tat-Seng Chua
Computer Vision
LensErase: A Foundation Model for Erase Anything
Yunuo Chen, Xiuyu Wu, Qinhong Yang et al. (+11 more)
We introduce LensErase, a general-purpose mask-based Erase Anything foundation model designed to cover a broad spectrum of real-world erase scenarios. LensErase supports diverse objects, visual text, watermarks, associated visual effects, multiple-object removal, and a wide range of object scales, aspect ratios, and image resolutions. First, to enable such broad coverage, we construct LensErase-100M, a large-scale
dataset containing 101.07 million paired source-mask-target examples spanning diverse erase scenarios. Second, we pretrain LensErase from the text-to-image model Lens, adapting its strong generative prior to mask-based erasing. To efficiently incorporate the source image and erase mask, we propose Mask-Aware RoPE, a 3D rotary positional encoding that directly injects mask information into the source-image
tokens without introducing a separate mask
token sequence. Finally, we refine the model through supervised fine-tuning and reinforcement learning with contract-guided, region-aware rewards, and apply TraceFusion at inference to preserve high-fidelity content outside the effective edit region. Across six public
benchmarks and the proposed LensErase-Bench, LensErase achieves substantial improvements under both reference-based objective metrics and reference-free VLM evaluation. We hope LensErase can serve as a foundational model for erase-related applications and systems.
Read the full abstract ▾
All authors Yunuo Chen, Xiuyu Wu, Qinhong Yang, Jinjing Zhao, Yanchen Dong, Sirui Zhang, Dong Chen, Fangyun Wei, Lei Shi, Ji Li, Dongdong Chen, Guo Lu, Yan Lu, Baining Guo
Data Structures and Algorithms
On the Parameterized Complexity of Capacitated Stack and Queue Layouts with Colored Edges
Thomas Depian, Giuseppe Liotta, Fabrizio Montecchiani et al. (+1 more)
Stack and queue layouts are two extensively studied and complementary linear representations of graphs. A stack (queue) layout $\langle \prec, \sigma \rangle$ of a graph $G$ consists of a total ordering $\prec$ of its vertices and of a partitioning $\sigma$ of its edges into pages, such that no two independent edges on the same page cross (nest). We propose a generalized model with colored edges (one color per edge) and capacitated pages. Namely, the input graph is equipped with colored edges and a prescribed budget for each page-color pair $(p,c)$ - this budget determines the maximum number of edges of color $c$ that page $p$ can accept. This model is motivated by fair allocation scenarios where budgets can be used to control the share of monochromatic edges on each page. Unfortunately, it is known that deciding whether a stack (queue) layout exists is NP-hard already with two (one) pages. Thus, we focus on the fixed-order setting - where the linear order $\prec$ is part of the input - for which an ordinary 2-page stack or $\ell$-page queue layout can be computed in
polynomial time. Despite the restrictive setting, we show that both capacitated problems are NP-complete already for two pages. Furthermore, we study the complexity of the problems when parameterized by the number of pages, colors, and/or the structure of the edge conflict graph with respect to the fixed linear order $\prec$. Our analysis paints a detailed complexity landscape and uncovers a surprisingly intricate interplay between the considered parameters.
Read the full abstract ▾
All authors Thomas Depian, Giuseppe Liotta, Fabrizio Montecchiani, Martin Nöllenburg
Computation and Language
From Agents to Edges: Paired Optimization for Multi-Agent Collaboration
Feng Lin, Xiaotian Yu, Yifan Yang et al. (+1 more)
Strong individual
agents do not guarantee effective collaboration. Communication must align what one
agent conveys with how another interprets and uses it. This dependency makes the communication edge a natural unit of optimization. We introduce Paired Automated Communication Optimization (PACO), which jointly optimizes the instructions at both ends of each edge and their shared communication convention in systems built on black-box
language models. PACO keeps model weights,
agent roles, and workflow
topology fixed. A state-aware discounted bandit selects edges for refinement, while execution feedback guides paired revisions evaluated through staged end-to-end execution. The optimized instructions integrate into existing
agent prompts without additional model calls at deployment. On a four-
agent workflow evaluated across diverse multi-
agent benchmarks, PACO consistently outperforms leading
prompt-optimization and communication baselines. Configurations learned on HotpotQA retain their advantage in cross-
dataset transfer without target-specific optimization. These results demonstrate that optimizing how
agents communicate can substantially improve collaboration within an otherwise fixed system.
Read the full abstract ▾
All authors Feng Lin, Xiaotian Yu, Yifan Yang, Aijun Li
Artificial Intelligence
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Hang He, Linting Wang, Guanming Liu et al. (+14 more)
Scaling interactive environments is important for training long-horizon
agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing construction pipelines offer limited support for such iterative refinement while keeping these components aligned. We introduce WorkRover, a framework for training long-horizon cowork
agents through recursive environment
evolution. Its harness-driven synthesis enables construction
agents to jointly build and validate semantically aligned work contexts, executable tasks, and evidence-grounded verifiers, adapting their actions to workspace state and execution feedback rather than following a fixed construction workflow. To support environment
evolution, we introduce Factorial Compatibility Replay (FCR), which uses rollout feedback to evaluate combinations of component revisions through dependency-closed replay and selects the smallest validated repair among tested candidates while preserving task requirements and evaluation constraints. To provide finer-grained training signals, we propose Verifier-to-Turn Credit Assignment (VTCA), which augments trajectory-level GRPO advantages with signals from deterministic workspace-progress checks and assigns a bounded share of positive-progress credit to prerequisite turns using recorded tool-output and artifact dependencies. Using WorkRover, we post-train Qwen3.5-35B-A3B to obtain WorkRover-35B-A3B and evaluate it on several cowork-
agent benchmarks. Its reported scores exceed those of Qwen3.5-35B-A3B by 26.27 percentage points on JobBench, 29.32 percentage points on OfficeQA Pro, and 413.25 Elo points on GDPval v2. These results suggest that WorkRover offers a promising foundation for scalable training of long-horizon cowork
agents.
Read the full abstract ▾
All authors Hang He, Linting Wang, Guanming Liu, Bo Mao, Jinxiu Liu, Yiran Suo, Maosen Zhou, Zhiheng Xi, Guanting Dong, Zhou Shao, Rui Zheng, Jie Zhou, Chengcheng Wan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang