IMLE‑VLA replaces the iterative action head in vision‑language‑action policies with a single‑step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). This eliminates multi‑step sampling, boosting inference frequency by 3.67× (55 Hz vs. 15 Hz) and achieving the highest average success rate (98.0 %) on the 40‑task LIBERO benchmark while maintaining robustness under perturbations. Real‑world tests on a Franka Emika Panda show smoother, faster motions and a 3.9×–6.6× reduction in inference time per episode.
By Kian Hosseinkhani (Simon Fraser University), Qinhe Peng (University of Pennsylvania), George Shramko (Simon Fraser University), Mehran Aghabozorgi (Simon Fraser University), Jianing Qian (University of Pennsylvania), Tristan Engst (Simon Fraser University), Alireza Moazeni (Simon Fraser University), Dinesh Jayaraman (University of Pennsylvania), Ke Li (Simon Fraser University, Canada CIFAR AI Chair)
The paper introduces SSS, a semi‑supervised framework that builds on the Vision Foundation Model SAM‑2 to improve medical image segmentation. It combines a weak‑to‑strong consistency regularization with a Discriminative Feature Enhancement mechanism and a prompt generator that uses Physical Constraints with a Sliding Window to supply prompts for unlabeled data. Experiments on the ACDC and BHSD datasets show that SSS outperforms prior methods, achieving a 53.15 Dice score on BHSD, a +3.65 improvement over the state of the art.
By Hongjie Zhu, Xiwei Liu, Rundong Xue, Zeyu Zhang, Yong Xu, Daji Ergu, Ying Cai, Yang Zhao
MedGEN-Bench is a new benchmark for open‑ended multimodal medical generation that addresses limitations in current medical visual benchmarks, such as query‑image misalignment, closed‑ended answer spaces, and text‑centric outputs. The dataset contains 6,422 image‑text pairs across six imaging modalities, 15 clinical tasks, and 27 subtasks, including VQA, image editing, and contextual multimodal generation pairs. Evaluation combines reference‑based fidelity metrics with a structured, checklist‑guided assessment by a medical VLM judge, and preliminary results show that image‑output tasks remain unsaturated while contextual augmentation improves image‑instruction similarity.
By Junjie Yang, Yuhao Yan, Gang Wu, Rui Qian, Zhisheng Chen, Haijiang Li, Yuhe Wu, Qichao Zhao, Dawen Tian, Xiang Wan, Fenglei Fan, Wenjian Qin, Yongquan Zhang, Feiwei Qin, Changmiao Wang
The paper introduces the Gaussian Belief Propagation Network (GBPN) for depth completion, a hybrid framework that combines deep learning with probabilistic graphical models. GBPN constructs a scene‑specific Markov Random Field via a Graphical Model Construction Network, then infers dense depth distributions using Gaussian Belief Propagation with a serial & parallel message passing scheme. Experiments show GBPN achieves state‑of‑the‑art performance on NYUv2 and KITTI, demonstrating robustness and generalizability across different sparsity levels and patterns.
By Jie Tang, Pingping Xie, Jian Li, Ping Tan
FujinSplat is a method for reconstructing clean 3D scenes from images captured through smoke by operating in the RAW image domain, where the camera’s ISP and the medium’s scattering effects remain separable. It first learns a per‑scene base ISP from hazy RAW captures, then uses a low‑dimensional correction space to fit per‑view corrections at training poses, and finally trains a scene‑agnostic controller to predict these corrections from RAW input. The corrected views supervise a single static 3D Gaussian representation, with a bounded per‑view residual to reconcile cross‑view inconsistencies, achieving superior performance on the RealX3D smoke benchmark compared to physics‑based and restoration‑then‑3DGS baselines.
By Gengjia Chang, Ziteng Cui, Shuhong Liu
SegKAN is a new model for high‑resolution medical image segmentation that tackles fragmentation and noise in hepatic vessel CT scans. It replaces the standard embedding module with a novel convolutional network to smooth noise and avoid gradient explosion, and reinterprets spatial relationships between Patch blocks as temporal relationships to better capture positional dependencies. Experiments on a hepatic vessel dataset show a 1.78% improvement in Dice score over the current state‑of‑the‑art model, indicating that the new structure enhances segmentation performance for extended objects.
By Shengbo Tan, Rundong Xue, Shipeng Luo, Zeyu Zhang, Xinran Wang, Lei Zhang, Daji Ergu, Zhang Yi, Yang Zhao, Ying Cai
DefVINS is a visual‑inertial odometry pipeline tailored for deformable scenes, breaking the rigidity assumption of traditional VIO. It decomposes the odometry state into a rigid, IMU‑anchored component and a non‑rigid scene warp using an embedded deformation graph. The authors also introduce VIMandala, the first real‑world benchmark with ground‑truth camera poses for deformable VIO, and extend the synthetic Drunkard’s benchmark with inertial data, demonstrating that DefVINS outperforms both rigid and non‑rigid baselines.
By Samuel Cerezo, Javier Civera
The paper presents a decision‑focused active learning framework for optimizing scale‑aware recovery of critical materials, using data from the Pacific Northwest National Laboratory’s CICERO workflow on autonomous selective precipitation. By adaptively selecting experiments based on prior results, the method achieves the best recorded enrichment of recycled neodymium‑iron‑boron magnets with roughly half the number of experiments compared to non‑adaptive approaches, and demonstrates similar efficiency for samarium‑cobalt magnets. The authors propose a Bayesian risk‑based batch selection strategy and outline a prospective test plan with standardized logging and economic validation.
By Niranjan Srinivas, Debajyoti Ray, Elias Nakouzi
Quantum Tiq‑Taq‑Toe is a popular benchmark for quantum computing and machine learning, yet no reinforcement learning (RL) methods have been applied to it. The paper introduces RL techniques for this game, which is simpler than Quantum Chess but still challenging due to partial observability and exponential state complexity. States are represented by a 3×3 measurement matrix and a 9×9 move‑history matrix of entanglement relations, making strategy development difficult because each move can collapse the quantum state.
By Catalin-Viorel Dinu, Thomas Moerland
The paper introduces GenQAS, a tensor network‑guided reinforcement learning framework that uses a learned local transition model to generate synthetic circuit transitions for prioritized generative replay. By mixing these synthetic transitions with real experience during Double Deep Q‑Network updates, GenQAS addresses sample starvation in quantum architecture search. Across benchmarks ranging from 6 to 15 qubits, the method improves success probabilities, identifies compact circuits, and reduces steps to chemical accuracy by up to 92.7%.
By Akash Kundu, Amit Kumar Jaiswal, Sebastian Feld, Prayag Tiwari
TART is a modular four‑stage pipeline that transcribes guitar audio into tablature, addressing key limitations of existing systems such as missing expressive techniques, incorrect string‑fret assignments, and poor performance on noisy recordings. The stages include an audio‑to‑MIDI model, an expressive technique classifier, an audio‑conditioned T5 encoder‑decoder for string‑fret mapping, and an automated tablature generator. In zero‑shot evaluations on GuitarSet, EGDB, and noisy variants, TART outperforms prior baselines with significant gains in audio‑to‑MIDI, string‑fret, and end‑to‑end tablature metrics.
By Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli
The paper introduces HorizonMath, a benchmark of 113 largely unsolved mathematical problems across eight domains, paired with an open-source framework for automated verification. It focuses on the generator‑verifier gap, targeting problems that are hard to discover but easy to verify computationally, thereby avoiding costly formal proof verification or manual review. Using this framework, the authors found six novel solutions—three each from GPT‑5.4 Pro and GPT‑5.6 Sol—demonstrating that current models can contribute to mathematical research, while most state‑of‑the‑art models score below 10%.
By Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Jakob Foerster, Cheng Zhang, Flaviu Cipcigan, Philip Torr, Alessandro Abate
The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.
By Tuan Nguyen, Qiran Hu, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai
The paper introduces Narrative Consolidation, a new NLP task that aims to merge overlapping narrative documents—such as legal testimonies or historical accounts—into a single, chronologically coherent text, rather than merely compressing them. It defines the task, proposes an evaluation framework, and presents the Gospel Consolidation Language Resource, a benchmark built from the four Biblical Gospels with 169 canonical events and cross‑document alignments. Experiments show that providing an explicit temporal backbone dramatically improves performance, a simple length heuristic outperforms graph‑based methods, and temporal edges are the key discriminative signal.
By Roger A. Finger, Eduardo G. Cortes, Sandro J. Rigo, Gabriel de O. Ramos
The paper introduces a method that transforms knowledge graph facts into a fixed vocabulary representation, where each fact becomes a node linked to its subject, object, and relation type via six meta-relations. Using this representation, standard GNNs (e.g., GAT, GINE, GraphSAGE, R-GCN) trained on a single small graph can achieve zero‑shot link prediction on 40 inductive benchmarks, matching the performance of specialized foundation models like ULTRA. The approach also generalizes to relational databases, enabling foreign‑key prediction without cell values or schema text, and the authors provide code, checkpoints, and evaluation tools for all benchmarks.
By Camille Pradel
LLMAR is a tuning‑free recommendation framework designed for sparse, text‑rich industrial B2B domains. It transforms user behavioral history into structured semantic motives using LLM inference, employs a reflection loop to self‑correct hallucinations, and operates cost‑effectively with asynchronous batch processing. Experiments on MovieLens‑1M, Amazon Prime Pantry, and a construction risk dataset show LLMAR surpasses state‑of‑the‑art learning models, achieving up to a 54.6% nDCG@10 improvement while keeping inference costs around $1 per 1,000 users.
By Ryogo Hishikawa, Ichiro Kataoka, Shinya Yuda
The paper introduces techniques for measuring the robustness of predictions made by two generative classifiers—naive Bayes classifiers and generative forests—whose underlying models are probabilistic graphical models. Robustness is defined as the degree to which the classifier’s distribution can be perturbed without altering its prediction, with perturbations explored via epsilon‑contamination, total variation distance, and chi‑squared divergence neighborhoods. Experiments on benchmark datasets show that the computed robustness values can serve as indicators of prediction trustworthiness and are compared against other existing indicators.
By Adri\'an Detavernier, Jasper De Bock
DeFiFlowBench is a benchmark comprising 207 natural‑language prompts for synthesizing DeFi workflows, evaluating graph coverage, configuration completeness, and declared safety predicates, and testing trade configurations on a local EVM. The study shows that direct, constrained, and few‑shot prompting still yield unsafe executions, and that a slippage bound derived from a quote does not prevent price impact. The proposed Koan‑Safe system—combining a prompt‑only intent parser, a replaceable generator, and structural repair—achieves a higher static safety proxy score and records no unsafe executions on the benchmark, while ablation studies reveal the limits of default safety thresholds and the need for explicit trade protections.
whyItMatters":"The results demonstrate that current prompting methods can still authorize costly trades and that explicit safety mechanisms like Koan‑Safe are necessary to prevent unsafe DeFi workflow executions."
By Abhinav Rajeev Kumar, Harshit Arora, Varun Singh, Manikandan Nanjappan
The paper introduces looped flows, a new approach that trains looped models using local denoising objectives to overcome the difficulty of training early updates for future ones. By enforcing temporal association through progressively decreasing noise levels and shared noise, the method encourages recurrent states to transfer useful computation over time. Inference is framed as integrating the velocity of a probability flow parameterized by the learned denoiser, allowing the model to solve harder problems by allocating more computation and producing multiple valid predictions from different initial noise samples. Across six reasoning benchmarks, looped flows outperform prior state‑of‑the‑art looped models, achieving 58.8% accuracy on ARC‑AGI‑1 and 12.2% on ARC‑AGI‑2.
By Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom, Nicholas M. Boffi, \.Ismail \.Ilkan Ceylan, Jinwoo Kim
The paper investigates whether inexpensive spectral metrics from the heavy‑tailed self‑regularisation framework can predict membership inference attack (MIA) vulnerability, offering a scalable alternative to costly shadow‑model attacks. Experiments on image and tabular classification tasks show that stable rank correlates positively with overall MIA success, while Log alpha‑Norm correlates negatively with MIA risk in low false‑positive regimes, outperforming conventional generalisation gap measures. These findings suggest that neural network spectra contain privacy leakage signals not captured by traditional overfitting metrics, pointing to spectral analysis as a promising direction for privacy auditing.
By Richard J. Preen, Jim Smith