Moonworks Lunara is a text‑to‑image model that defines Artistic Intelligence as exploration‑driven world realization, preserving semantic, artistic, and compositional structure. It uses a Diffusion Mixture Transformer architecture and a training algorithm that iteratively refines the data distribution with informative samples and human‑created art. Benchmarks show Lunara ranks first in aesthetic quality and second in emotional resonance against seven other image‑generation models, while maintaining a sub‑10B parameter size and sub‑10‑second inference latency.
By Yan Wang, Yanzu Wang, Maitreyee Joshi, Samiha Sadeka, Partho Hassan, Reza Jarral, Sayeef Abdullah, Sabit Hassan
The paper introduces Spectral Transductive Refinement (STR), a training‑free method that refines class prototypes at test time using the geometry of a joint k‑nearest‑neighbour graph and a normalized‑Laplacian spectral coordinate system. STR operates solely on frozen visual embeddings, iteratively updating pseudo‑labelled queries to improve one‑shot and few‑shot classification under domain shift. Experiments on ResNet‑18 and ResNet‑10 backbones show STR outperforms single‑prototype baselines and rivals meta‑trained cross‑domain few‑shot methods, achieving the best 1‑shot average across eight target domains.
By Fahim Rahman, S. M. Tanjeeb Meheran Rohan, Md. Taimum Ibne Sayed, Asaduzzaman Herok, Md. Bakhtiar Hasan
The paper introduces Chart‑RVR, a reinforcement‑learning framework that trains chart‑reasoning agents to produce monitorable, verifiable outputs. It decomposes reasoning into three auditable stages—Structure, Evidence, and Derivation—allowing stakeholders to trace how the model reads the chart, extracts data, and computes the answer. Experiments on six benchmarks show that Chart‑RVR matches or exceeds state‑of‑the‑art accuracy while delivering rationales that are far more verifiable and evidence‑grounded than existing methods.
By Sanchit Sinha, Oana Frunza, Kashif Rasul, Aidong Zhang
The paper studies classifier‑free guidance (CFG) in Flow Matching, showing that strong guidance can distort the generated distribution by shifting the mean and concentrating trajectories. By interpreting Flow Matching as a time‑varying gradient flow, the authors explain how CFG reshapes the underlying potential and propose a training‑free method, Posterior‑Mean‑Capped CFG (PMC‑CFG), that adaptively limits guidance to the strongest feasible level. Experiments on synthetic and large‑scale image‑generation tasks demonstrate that PMC‑CFG reduces distortion and concentration while improving the alignment–diversity trade‑off, especially when nominal guidance is large.
By Jishen Peng, Zheng Ma
The paper introduces LiDAR-Hallu, a benchmark with 10,000 questions designed to test 4D LiDAR language models on spatio-temporal reasoning. It shows that models often achieve high multiple-choice accuracy by exploiting trivial patterns, such as always selecting the same option or relying on candidate duration, rather than truly understanding object relationships. Detailed analysis reveals systematic failures, especially in lateral-motion cases and opposite-answer scenarios, indicating that aggregate accuracy masks underlying reasoning gaps.
By Runyi Yang, Murat Akkoyun, Di Wen, Ruiping Liu, Yufan Chen, Junwei Zheng, Xiaoye Wang, Kailun Yang, Danda Pani Paudel, Luc Van Gool, Kunyu Peng
The paper introduces Bidirectional Reciprocal Learning (BRL), a parameter‑efficient fine‑tuning framework for referring image segmentation that operates on frozen vision foundation models. BRL employs two lightweight adapters—Reciprocal Attention Adapter (RAA) for token‑level cross‑modal attention and Reciprocal Gate Adapter (RGA) for channel‑level gating—to enable hierarchical, bidirectional information flow between vision and language. Experiments on RefCOCO, RefCOCO+, and RefCOCOg show that BRL outperforms existing methods while updating fewer than 0.5% of backbone parameters.
By Xiaoqiang Lu, Licheng Jiao, Lingling Li, Yuting Yang, Long Sun, Wenping Ma, Xu Liu, Fang Liu
VideoGen-Agent is a multimodal agent that uses multitask agentic reinforcement learning to coordinate external tools for video generation. It learns to augment, generate, and verify videos through multi‑turn interactions, guided by prompts and intermediate observations. On the new VABench benchmark, the agent improves base text‑to‑video performance by 19.1 points, and further upgrades to generation tools raise the score to 86.1, with human raters favoring the upgraded configuration in 84.3% of comparisons.
By Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Suozhi Huang, Xiangyi Li, Yu Li, Chunyuan Li, Shilong Liu, Mengdi Wang
The paper introduces the ACE framework, which uses spatially explicit inspection to guide embodied exploration. By combining evidence‑grounded perception with exposure‑informed movement, ACE provides a spatially resolved decision paradigm that improves cue assessment and movement direction. Experiments show ACE boosts navigation task success by 18.0% and exploration efficiency by 10.3% over previous baselines.
By Wenbin Wang, Xiang Bai, Yizhao Wang, Hang Sun, Dong Ren, Jie Qin, Qingquan Li, Bing Wang
The paper introduces ProAction, a multimodal dataset of 10,000 samples comprising visual, audio, and text inputs across 12 daily-life scenarios, designed to support the Proactive Robot Action Reasoning (ProRobo) problem. It presents a two-stage human-in-the-loop annotation pipeline that incorporates appraisal and Theory-of-Mind considerations to generate cognitively grounded high-level action labels. The authors benchmark multimodal large language models and propose MMC2Act, showing that training on ProAction significantly improves proactive action reasoning compared to general-purpose models.
By Zhihao Gu, Kechao Zhu, Yuanfeng Wu, Mohan Liu, Ankit Kumar Shaw, ChenDong Hong, Xuanyu Chen, Dengchen Mei, Xu Tianyi, Lin Wang
The paper introduces GradCIR, a method for training composed image retrieval (CIR) systems on graded relevance rather than binary relevance. It uses a vision‑language model to generate queries and 4‑level relevance labels, an iterative feedback loop to mine hard negatives, and a hierarchy‑aware angular objective to directly optimize graded labels. Experiments on a Walmart catalog and FashionIQ show significant NDCG improvements and the system is deployed in Walmart’s live visual‑search traffic.
By Anubhav Gupta, Hrushikesh Mohapatra, Prijith Chandra, Asish Mohapatra, Anuj Garg, Arvind Maan, Sudip Datta, Venkat Bulusu, Sitesh Kumar Jalan
arXiv:2609.22947v1 Announce Type: new
Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, exist...
By Zhenchen Tang, Yang Li, Songlin Yang, Bo Peng, Xiaotong Zhao, Shuai Li, Haotian Fan, Alan Zhao, Jing Dong
SolarFlowRefiner is a refinement‑aware flow‑matching framework designed to downscale high‑resolution surface solar radiation (SSR) fields from coarse ERA5 radiative variables and satellite channels. It first uses a conditional FlowMatch generator to predict a normalized correction to an upsampled ERA5 baseline, then trains a refiner on prediction‑conditioned states between the generator’s output and the target residual, exposing the refiner to the generator’s structured errors. The refinement objective is backpropagated through the FlowMatch sampler, enabling joint optimization of generation and correction, and experiments on an ERA5–SolarCube benchmark demonstrate consistent improvements over standalone generation and post‑hoc refinement.
By Udbhav Srivastava, Antonita Racheal, Yiheng Chen, Runlong Yu, Xinyue Ye
SafeTune is a source‑available library that consolidates four safety‑intervention paradigms—post‑hoc weight recovery, safety‑constrained fine‑tuning, gradient‑based unlearning, and inference‑time steering—into a single, configuration‑driven workflow. It offers shared interpretability, evaluation, and deployment tools, and its modular registry allows easy addition of new methods, benchmarks, judges, models, and fine‑tuning domains. The authors demonstrate SafeTune with controlled comparisons and case studies in finance and medical deployments, showing how it characterizes safety drift, evaluates interventions on refusal‑behavior and capability metrics, and supports calibrated or layered mitigation.
By Pratinav Seth, Saisab Sadhu, Anshul Kaushal, Vinay Kumar Sankarapu
TARGet is an open‑source, topology‑aware machine‑learning framework for modeling RF circuits. It uses S‑parameter representations of sub‑circuits and a fusion architecture that combines Graph Neural Networks with sub‑circuit connectivity‑aware networks, enabling learning across multiple topologies. Experiments show TARGet achieves sub‑1% prediction error, reduces training data needs by up to 35.5×, and improves accuracy by 9.7× over state‑of‑the‑art models, with zero‑shot transfer to unseen sub‑circuit topologies.
By Soroosh Noorzad, Sebastian Bodero, Morteza Fayazi
Toollery is a training‑free framework that compresses candidate lists for large language model agents, enabling efficient selection from thousands of skills and tools. It generates user‑intent queries from each skill or tool specification, builds a retrieval index, and limits online selection to a compact top‑k set before the LLM makes its final decision. Evaluations on the SkillRouter benchmark, BFCL‑V4, and a proprietary smart‑cockpit dataset show that Toollery improves recall and end‑to‑end selection while keeping selection costs bounded.
By Xiangxi Tian, Ran Guan
The paper investigates why large language models often miscount items in bracketed lists. It finds that different instruct models exhibit distinct error patterns—Qwen and Gemma 27B tend to round odd lengths to nearby even numbers, OLMo focuses errors on mid-sized integers, and Llama under‑counts—challenging the idea that a single cause explains all failures. The study also shows that a linear probe can recover the correct count from the residual stream and that fixes effective for one model may not transfer to others.
By Iyad Ait Hou, Saad Mankarious, Aya Zirikly, Rebecca Hwa
The paper introduces Physics‑SIMS‑TS, a conditional diffusion model designed for long‑horizon oil and gas production forecasting. It enforces monotone decline through negative guidance, decline‑curve constraints, and isotonic projection during sampling, and incorporates spatial training augmentation and an ensembled stochastic sampler to produce calibrated predictive distributions. Evaluated on over 35,000 wells across three jurisdictions, Physics‑SIMS‑TS achieves the highest accuracy among diffusion forecasters and matches transformer ensembles, with only a 0.5% increase in mean squared error for monotonicity.
By Temesgen Mikael Abraha, Yves Lucet
arXiv:2609. 22690v1 Announce Type: new Abstract: We develop an index policy for finite-horizon Bernoulli multi-armed bandits from minimax solutions to single-arm bandit (SAB) problems.
By Huikang Liu, Zhengchao Wang, Daniel Kuhn, Wolfram Wiesemann
The paper introduces a counterfactual tool ranking framework that accounts for authority, historical support, and estimation nuances. Using eleven enterprise-inspired tools, synthetic and real-world experiments on the Berkeley Function Calling Leaderboard, the study compares direct regression and doubly robust (DR) methods, finding that DR performs better in shifted environments while direct regression excels in linear settings. The authors also evaluate Qwen2.5 models on held-out tasks, analyze policy differences under missing support, and present a falsifiable evaluation method with publicly available evidence.
By Jiapeng Li
Causilo is a new tabular foundation model that delivers state‑of‑the‑art predictive performance while achieving exceptionally fast inference. On the TabArena benchmark it scores 1785.4 Elo with a median inference time of 0.10 seconds per 1 K test samples, outperforming TabPFN‑3.5‑Fast by 31.6% in speed and reaching the performance–efficiency Pareto frontier. The architecture builds on TabICL’s column‑then‑row design, adding a row‑refinement module that exchanges information among cell representations before a final column stage, and uses cross‑attention with a fixed number of summary tokens to keep attention cost linear in the number of features.
By Minyong Cho, Minho Jeong, Dooho Lee, Jinmo Lee, Jaemin Yoo