Large Language Model judges are commonly used to rank texts via pairwise comparison, with reliability traditionally measured by position bias, transitivity, and pairwise agreement. This paper argues that these proxies are misleading because they are dominated by close‑rank‑gap pairs, which contribute little to the overall ranking, while far‑gap pairs carry the true ranking signal. Experiments on simulations and human‑rated corpora show weak correlation between the proxies and actual ranking accuracy, suggesting judges should be evaluated using rank‑gap‑conditional metrics against human rankings.
By Bruno Brocai, Maria Becker
Pixel diffusion models generate RGB images directly but tend to miss fine‑scale natural‑image statistics. The authors introduce an adversarial post‑training step that adds an adversarial loss to the model’s output at non‑high‑noise timesteps, without changing the architecture or sampling procedure. This approach improves distribution fidelity, coverage, prompt alignment, and perceptual quality across two pixel backbones, and restores missing high‑frequency spectral power while avoiding memorization or mode dropping.
By Xin Lin, Zhifei Zhang, Yuqian Zhou, Haitian Zheng, Zhe Lin, Ming-Hsuan Yang, Truong Nguyen
Large language models (GPT‑4o and Claude 3.7 Sonnet) were tested on two variations of a Bayesian reasoning task across 5 experiments and 5,000 trials. They performed near human levels on the task, but their reasoning was more rule‑based and rigid. The models also exhibited Bayesian hypocrisy, condemning others who used the same Bayesian reasoning, a human‑like error that highlights a dissociation between self‑performance and other‑judgment.
By Nykko Vitali, Mahzarin R. Banaji
arXiv:2609.36440v1 Announce Type: new
Abstract: Large vision-language models (LVLMs) have recently achieved remarkable progress across multimodal tasks, yet object hallucination remains a persistent...
By Jae-Ho Lee, Jeong-Eun Lee, Gyeong-Moon Park
arXiv:2609.36832v1 Announce Type: new
Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that...
By Ping Liu, Chi Zhang
arXiv:2609.36058v1 Announce Type: new
Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient method...
By Hsiao-Ru Pan, Florent Draye, Bernhard Sch\"olkopf
arXiv:2609.36061v1 Announce Type: new
Abstract: In quantitative finance, standard regression losses are misaligned with the economics of return prediction. As the conditional mean of financial log-re...
By Joel Pfeffer (Allora Foundation), J. M. Diederik Kruijssen (Allora Foundation), Florian Stecker (Allora Foundation), Steven N. Longmore (Allora Foundation, LJMU)
arXiv:2609.36064v1 Announce Type: cross
Abstract: Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly...
By Sahand Rezaei-Shoshtari, Patryk Wozniczka, Shu Ishida, Gregg Streuber, Farnoosh Javadi, Jeffrey Landes, Angela Ju, Muhammad Azam, Bryan Lim, Johan Luttun, Indrajeet Haldar, Jonathan Shaw, Beatriz Guerra, Ivan Sosnovik, James Stoddart, Robert Giaquinto, Adam Gaier
arXiv:2609.36813v1 Announce Type: new
Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. How...
By Chuanpu Liu, Miao Yu, Yikai Cai, Yuanhe Zhang, Zhenhong Zhou, Li Sun, Zuming Jiang, Yufei Guo
arXiv:2609.36890v1 Announce Type: new
Abstract: In scientific machine learning, physical fields governed by partial differential equations exhibit low-rank structure and scale invariance. When solvin...
By Kaichen Ouyang, Chenglei Yu, Chuanrui Wang, Tailin Wu
arXiv:2609.37065v1 Announce Type: new
Abstract: Decision-making under uncertainty often relies on predicted parameters, yet accurate prediction does not necessarily lead to good operational decisions...
By Jiahui Feng, Dafang Zhao, Zheng Chen, Zhengmao Li, Lingwei Zhu
arXiv:2609.37537v1 Announce Type: new
Abstract: Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive re...
By Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar, Matin Ghiasi, Ali Aghayari, Amirhossein Souri, Mohammad Mosayyebi, AmirMahdi Sadeghzadeh, Mohammad Hossein Rohban
arXiv:2609.35599v2 Announce Type: replace
Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
By Luke Leckie, Peter M. Todd, Jacob G. Foster
Vision‑Language Models (VLMs) used in autonomous driving are evaluated on their ability to understand velocity through three tasks: surrounding‑agent speed, current ego speed, and short‑horizon future ego‑speed. Experiments on nuScenes show that while current ego speed can be accessed internally, verbal outputs are poor and surrounding‑agent speed is weakly encoded; temporal cues and frame order are largely ignored. Specialized driving models (Alpamayo‑1.5) improve latent speed representations but still leave gaps between internal knowledge and verbal readout, indicating that good planning outputs do not guarantee reliable dynamic state recovery.
By Katharina Winter, Stefan Englmeier, Fabian B. Flohr
arXiv:2609.37694v1 Announce Type: cross
Abstract: Diffusion models have recently shown strong potential for probabilistic multivariate time-series forecasting by modeling complex conditional distribu...
By Rui Han, Min Yang, Xu Zhang, Xinghao Yang, Wei Liu, Yongshun Gong
Grounded Transitive RL (GTRL) is an offline goal‑conditioned reinforcement learning algorithm that improves upon divide‑and‑conquer value learning by grounding updates with a one‑step temporal‑difference (TD) target. By adding this TD target rather than replacing it, GTRL ensures every state‑goal pair receives an update and corrects bias from hindsight relabeling through reweighting based on reachability. The method was evaluated on nineteen OGBench tasks across stochastic, deterministic, and stitching environments, achieving the highest average success rate among compared approaches.
By Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman, Md Mehedi Hasan
PowerZooJax is a JAX-based benchmark suite designed for reinforcement learning in power system operation. It offers five constrained Markov decision process tasks covering generation, transmission, distribution, distributed energy resources, and data center microgrids. By implementing power flow, economic dispatch, market clearing, and device dynamics as JAX computation graphs, the entire training and evaluation loop runs on the GPU, yielding significant speedups over CPU-based simulations and enabling standardized evaluation of policy returns, safety violations, and out-of-distribution stress conditions.
By Zhanhua Pan, Xiao Liu, Zhilong Cao, Jianhong Wang, Dawei Qiu
CoRe introduces a co‑evolving reward framework to mitigate latent reward hacking in video diffusion models. By continuously refitting the latent‑reward model on the generator’s current samples and anchoring it to real‑video preferences, CoRe prevents the generator from drifting outside the reward model’s training support. Experiments on Wan2.1‑T2V‑1.3B demonstrate that CoRe improves generation quality over pretrained models and prior alignment methods while avoiding quality collapse.
By Zhaolong Su, Yujin Han, Feng Wang, Jameson Dong, Hins Hu, Difan Zou
Neural Structural Reasoner (NSR) is a brain-inspired neural network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. It incorporates multi-layered architecture, stable entity representations, and path integration to perform link prediction by parallelizing over candidate relational structures and using confidence-weighted scores. NSR achieves competitive accuracy on knowledge-graph benchmarks, trains faster than several neural baselines, and offers native interpretability by tracking human-readable neuron activations and extracting latent relational hierarchies and compositional rules.
By Zixing Jia, Yuhang Pan, Ni Ji
FairDiff is a new fairness‑aware diffusion framework designed to mitigate the self‑reinforcing Matthew Effect in Diffusion Recommender Models (DRMs). It introduces Popularity Condition Guidance (PCG) to reweight inference‑time gradients and penalize high‑popularity items, and a Semantic Calibration (SC) module that aligns forward and reverse distributions via optimal transport. Experiments show FairDiff achieves state‑of‑the‑art performance while reducing popularity bias in DRMs.
By Song-Li Wu, Xianquan Wang, Zhaocheng Du, Weinan Gan, Jingyi Wang