The paper introduces Spatial Memory Intelligence (SMI), a framework that enhances long‑video world models by systematically managing spatial memory using an understanding model. SMI employs four coordinated operations—spatial clustering, within‑cluster sparsification, action‑aware retrieval, and reliability‑aware filtering—to handle increasingly complex and lengthy memory sequences. Experiments across various baselines and benchmarks show that SMI improves memory sparsity, generation stability, and spatial consistency, demonstrating its effectiveness and generalizability.
By Ying Yang, Guiyu Zhang, Lianghua Huang, Chang Nie, Chenyang Si, Haofan Wang, Shaoshuai Shi, Li Jiang
CRISP is a framework that reconstructs the last‑layer activation vector of binary neural teachers into Tsetlin Machine clauses, enabling a symbolic trace from input thresholds to teacher neurons. It sign‑binarizes penultimate activations and assigns an Individual TM to each neuron, representing each hidden bit with propositional clauses over Booleanized inputs. Experiments on MNIST, KMNIST, FashionMNIST, SVHN, and CIFAR‑10 show that this binarization preserves teacher accuracy while the main limitation is reconstruction error, with quartile one‑bit Booleanization achieving the best fidelity on SVHN.
By Alex Chan, Shafi Muhtasim Chowdhury, Ekin Can Erku\c{s}, Ole-Christoffer Granmo, Alex Yakovlev, Rishad Shafik
arXiv:2610.03128v1 Announce Type: new
Abstract: Quantitative trading strategy design aims to discover trading programs from historical data that remain effective in future markets, which can be viewe...
By Chaoqun Yang, Qian Wang, Fengbin Zhu, Xinyu Lin, Bingsheng He, Roger Zimmermann, Tat-Seng Chua
The paper introduces a generative graph model that combines mechanistic interpretability with amortized inference by formulating both the generative process and parameter recovery in function space. It extends step graphons to a multifractal construction, enabling a neural inverse operator that can infer parameters for unseen graph sizes. Experiments show the model outperforms a pretrained graph foundation model on zero‑shot generation and matches instance‑specific methods on single‑observation networks, while also sensitively tracking brain state changes in an EEG study.
By Wooseong Choi, Italo'Ivo Lima Dias Pinto, Chen Sun, Gaurav Gupta, Dong Song, Paul Bogdan
DyadMem introduces a new benchmark for evaluating how long‑term agents remember user‑specific relational information, called User‑conditioned Relational Agent Memory (URAM). The dataset contains 3,065 episodes, 50,961 sessions, and 61,210 QA pairs, with detailed annotations for memory capture, update, and recall across multi‑session trajectories. Experiments on 20 models show strong performance in a gold‑memory setting but a significant drop in full‑pipeline QA, highlighting gaps in current LLM memory capabilities.
By Yifei Tao, Xinyu Zhong, Henry Hengyuan Zhao, Fanyi Wang, Tengda Guo, Wentao Qiu, Ying Wang, Liujian Tang
The paper introduces CreativePreferences, a large dataset of 2.8 million texts labeled by 317 million human preference judgments across seven creative domains, and explores how preference components that are tacit, articulable, and verifiable differ. By modeling these labels with executable programs, rubric banks, and densely trained models, the authors identify robust articulability and verifiability gaps—especially in domains like peer review and creative writing—and propose a novel measurement approach to estimate these gaps. The study demonstrates that fully articulated models can diverge from human preferences and that articulating preferences may shift them away from tacit dimensions, offering recommendations on task prompting and learning strategies.
"whyItMatters":"The findings highlight that current AI preference modeling may miss crucial tacit aspects, potentially leading to misaligned or suboptimal outcomes in creative and evaluative tasks."
By Alexander Spangher, Sheldon Huang, Andreas Haupt, Noah D. Goodman, Diyi Yang, Daniel E. Ho, Sanmi Koyejo
The paper introduces ComInsight, a method for generating analytical reports from relational tables by composing verifiable atomic insights. It defines atomic insights as minimal executable analytical units, enumerates them from the database schema, and organizes them into a multi-relational insight graph. Composition operators then fuse these atomic nodes into higher-order conclusions, each accompanied by executable SQL and fine-grained provenance, achieving superior factual correctness, novelty, and structural completeness on three benchmarks.
By Teng Lin, Xinyu Liu, Nan Tang
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
By David L. Condrey
The World Embedding Benchmark introduces 8,000 simulation-based video cases covering fluid, solid, dynamic, and optical physics, each paired with physical annotations. It supports three tasks—text‑video retrieval, physical‑property regression, and multiple‑choice classification—to assess how well video embeddings capture physical alignment versus quantitative information. Experiments show that while pre‑trained models perform poorly on retrieval and classification, lightweight probes can extract useful physical data, and physics‑specific contrastive training improves alignment but harms regression, highlighting a trade‑off. Retrieval‑augmented generation using these embeddings further enhances the physical fidelity of generated videos.
By Yiqi Liu, Ruifeng Yuan, Yang Wang, Long Li, Fengyu Cai, Hou Pong Chan, Jialin Yu, Hao Zhang, Chenghua Lin, Chenghao Xiao
BioMol-MQA is a new question‑answering dataset focused on polypharmacy that combines a multimodal knowledge graph—containing both text and molecular structure—with challenging questions designed to test large language models’ ability to retrieve and reason over this diverse information. The dataset highlights the limitations of current retrieval‑augmented generation systems, which typically handle only single‑modality text, by demonstrating that existing LLMs perform poorly unless provided with the necessary multimodal background data. This underscores the need for more robust RAG frameworks capable of integrating multiple data types for accurate responses.
By Saptarshi Sengupta, Shuhua Yang, Paul Kwong Yu, Fali Wang, Suhang Wang
The paper introduces Percept-V, a dataset of 6,000 program-generated images across 30 domains designed to test simple visual perception skills from the TVPS-4 framework. Experiments show that state‑of‑the‑art multimodal large language models perform poorly compared to humans, especially as image complexity increases, and that fine‑tuning yields only limited generalization to related datasets. The study highlights specific perception skills that remain challenging for current models.
By Samrajnee Ghosh, Ashish Goswami, Naman Agarwal, Hemanshu Garg, Chinmay Mittal, Mausam, Parag Singla
The paper introduces MITE, a method that transforms biomedical named entity recognition (BioNER) into a structure‑to‑structure generation task by encoding instructions and outputs in multiple programming languages (Python, C++, Java). This approach provides structurally diverse supervision without extra biomedical knowledge, and during inference it aggregates predictions via entity‑level voting to reduce language‑specific variance. Experiments on six BioNER datasets show that MITE outperforms BERT‑based and LLM‑based baselines and generalizes well across datasets.
By Songtao Li, Yijia Zhang, Jianyuan Yuan, Shidi Zhang, Fengyu Zhang, Hongfei Lin
The paper introduces GAMA, a guideline-augmented multi-agent framework designed to improve biomedical named entity recognition (BioNER) using large language models (LLMs). GAMA constructs dataset-specific guideline memory by inducing and verifying annotation rules from training data, then employs a planning component to generate span-type hypotheses with rationales, a coding component to produce schema-constrained entity objects, and a verification module for structural compliance and dual-loop refinement. Experiments across five BioNER datasets demonstrate that GAMA consistently outperforms strong LLM-based baselines, with ablation studies confirming the effectiveness of each component.
By Songtao Li, Yijia Zhang, Shidi Zhang, Jianyuan Yuan, Fengyu Zhang, Hongfei Lin
The paper introduces a PyTorch library that unifies 55 hyperspectral image models across six deep‑learning paradigms, providing a common registry, automatic tensor adaptation, and standardized constructors. It includes 24 benchmark scenes from various sensors, with tools for data preprocessing, patch extraction, and rigorous train‑test partitioning to avoid overlap. Experiments on 1,320 model‑scene combinations show that scene difficulty outweighs architecture choice, with no single paradigm dominating and small models performing competitively with much larger ones.
By Tanishq Rachamalla, Aryan Das, Srishti Kaushik, Swalpa Kumar Roy
In-Distribution Forcing for Long Video Generation at Test Time introduces a test‑time framework that aligns KV caching and conditioning with training configurations to prevent out‑of‑distribution key‑value entries during long‑horizon video generation. The core technique, self‑caching, ensures each chunk is cached without attending to prior KV entries, keeping the rolling window exactly in‑distribution. This approach extends short‑horizon autoregressive video diffusion models to minute‑scale generation, outperforming prior methods in mitigating drifting as shown by drift metrics and a user study.
By Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo, Hyunmog Kim, Sungjoon Choi, Joonseok Lee, Jaewoong Choi, Jaemoo Choi
The paper presents a new approach to automatic skeleton generation that tackles two key challenges: encoding branch structures into token sequences and leveraging test-time computation. It introduces branch‑centric tokenization, a representation that groups structurally related elements together and directly encodes connectivity, producing more compact sequences than traditional BFS serialization. Additionally, the authors propose view‑augmented generation, a test‑time augmentation technique that rotates the input mesh, aligns predictions, and selects the best skeleton based on mesh coverage and consistency across views, leading to improved accuracy on benchmark datasets.
By Zhengyuan Li, Chuanyu Pan, Yuanming Hu, Raymond A. Yeh
EditHero is presented as the first benchmark for long-horizon, part-level 3D editing, featuring natural-language instructions and target images for both geometry and texture. The benchmark uses a deterministic assembly engine that produces the exact target after each edit, and every sequence is manually reviewed. It compares non-agentic top‑down methods with LLM/VLM agent bottom‑up approaches, finding that the latter follow instructions more closely and preserve unedited parts better, though each edit takes minutes.
By Ruihan Yu, Yu-Ju Tsai, Muyao Niu, Runyi Li, Lian Fu, Hanqing Liu, Zheng-Hui Huang, Yonghao Yu, Sho Kuno, Ming-Hsuan Yang, Kaipeng Zhang, Zhixiang Wang
SimuVerity is a new benchmark that evaluates text-to-executable Simulink model-generation tasks across ten engineering domains, using 101 tasks that include executable-system profiles and native simulation scenarios. The benchmark employs a hierarchical evaluator that first checks artifact delivery, native executability, and engineering qualification, then scores qualified models on six dimensions such as accuracy, output quality, mechanistic fidelity, control and causal integrity, operating-domain robustness, and dynamic response. In tests of six agent systems, the best achieved only a 42.86 overall score, revealing that structural similarity is a poor proxy for engineering performance and that high-scoring models can still have severe visual-layout disorder.
By Ruiqi Zhang, Jiahao Wang, Mingxuan Li, Haichen Luo, Chaoting Wang, Guoyu Mou, Keyu Lai, Hanchao Lv, Jiaxu Wang, Yibo Zheng, Aijun Yang, Xiaohua Wang
The paper introduces a Mixture-of-Agents (MoA) approach to quantify the per-token compute required by large language models. By having a panel of fifteen models of varying sizes attempt to reproduce each token, the authors define the smallest successful agent’s inference cost as the token’s sufficient compute, providing an upper bound on necessary computation. Experiments on benchmarks show that a 0.5B model can reproduce most tokens, and that the MoA-derived compute map can reduce latency in model routing and drafting tasks while improving or maintaining accuracy.
By Zhixu Du, Weijia Han, Hai Helen Li, Yiran Chen
The paper presents an expert‑validated benchmark of 1,042 items across ten areas of Colombian law to assess the reliability of large language models (LLMs) on national legal systems outside the U.S. It evaluates 15 contemporary proprietary and open‑weight models, finding that while closed‑choice accuracy can be high (up to 0.905), free‑text factual correctness never exceeds 0.45. The study reveals a strong dissociation between answer relevance and correctness, systematic variation by legal area, and suggests that expert supervision and grounding in authoritative sources are needed for reliable Colombian legal tasks.
By Rub\'en Manrique, Michelle Castellanos, Jorge Morales, Juan David Guti\'errez, Antonio Barreto Rozo, Joaqu\'in V\'elez Navarro