cs papers | Gist.Science

A Miniature Brain Transformer: Thalamic Gating, Hippocampal Lateralization, Amygdaloid Salience, and Prefrontal Working Memory in Attention-Coupled Latent Memory

This paper introduces a miniature brain transformer architecture that demonstrates a novel, falsifiable prediction: functional lateralization of hippocampal banks requires the synergistic interaction of a prefrontal working-memory buffer (acting as a symmetry-breaker) and inhibitory callosal coupling, a mechanism that triggers a sharp phase transition in memory performance while a cerebellar fast-path merely accelerates convergence.

Hong Jeong2026-03-10💻 cs

VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization

VINO is a self-supervised learning framework that overcomes the "co-occurrence trap" in dense video by using a teacher-student distillation approach with structural priors to force representations to focus on foreground objects rather than background context, achieving state-of-the-art unsupervised object discovery performance.

Seul-Ki Yeom, Marcel Simon, Eunbin Lee, Tae-Ho Kim2026-03-10💻 cs

A Hybrid LTR-based System via Social Context Embedding for Recommending Solutions of Software Bugs in Developer Communities

This paper proposes a hybrid Learning-to-Rank recommender system that leverages deep learning and social context embeddings from Stack Overflow to effectively recommend software bug solutions to developers, achieving nearly 78% accuracy in the top 10 results.

Fouzi Harrag, Mokdad Khemliche2026-03-10💻 cs

Single Image Super-Resolution via Bivariate `A Trous Wavelet Diffusion

This paper introduces BATDiff, an unsupervised single-image super-resolution model that leverages bivariate A-trous wavelet transforms and cross-scale parent-child dependencies to generate sharper, more structurally consistent high-frequency details while minimizing artifacts and dataset-driven hallucinations.

Heidari Maryam, Anantrasirichai Nantheera, Achim Alin2026-03-10💻 cs

Novel Table Search [Technical Report]

This paper addresses the unexplored challenge of avoiding redundancy in data lakes by defining the Novel Table Search (NTS) problem, proposing an efficient penalization-based approximation algorithm called ANTs, and demonstrating through extensive experiments that it outperforms existing methods in capturing syntactic novelty while maintaining low execution time.

Besat Kassaie, Renée J. Miller2026-03-10💻 cs

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

The paper proposes HY-WU, a memory-first adaptation framework that replaces static weight overwriting with a functional neural memory module to synthesize instance-specific weight updates on-the-fly, thereby enabling robust continual learning and personalization without degrading previously learned behaviors.

Tencent HY Team2026-03-10💻 cs

Reinforcement Learning for Vehicle-to-Grid Voltage Regulation: Single-Hub to Multi-Hub Coordination with Battery-Aware Constraints

This paper proposes a soft actor-critic-based reinforcement learning framework for vehicle-to-grid voltage regulation that effectively coordinates single and multi-hub charging systems while prioritizing battery health and fleet availability, demonstrating robust performance comparable to standard droop controllers under both nominal and aggressive overloading conditions.

Jingbo Wang, Roshni Anna Jacob, Harshal D. Kaushik, Jie Zhang2026-03-10💻 cs

FabricGen: Microstructure-Aware Woven Fabric Generation

FabricGen is an end-to-end framework that generates realistic woven fabric materials from text by decoupling macro-scale texture synthesis via fine-tuned diffusion models from micro-scale weaving pattern generation using a specialized LLM-driven procedural geometric model.

Yingjie Tang, Di Luo, Zixiong Wang, Xiaoli Ling, jian Yang, Beibei Wang2026-03-10💻 cs

PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation

This paper introduces PresentBench, a fine-grained, rubric-based benchmark comprising 238 instances and detailed binary checklists that enables more reliable, human-aligned evaluation of automated slide generation, revealing that NotebookLM currently outperforms other methods in this domain.

Xin-Sheng Chen, Jiayu Zhu, Pei-lin Li, Hanzheng Wang, Shuojin Yang, Meng-Hao Guo2026-03-10💻 cs

LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture

This paper introduces LEPA, a learned architecture that conditions on geometric augmentations to accurately predict transformed satellite image embeddings, effectively overcoming the limitations of standard interpolation in non-convex geospatial foundation model manifolds and significantly improving geometric adjustment performance.

Erik Scheurer, Rocco Sedona, Stefan Kesselheim, Gabriele Cavallaro2026-03-10💻 cs

Learning When to Cooperate Under Heterogeneous Goals

This paper addresses the challenge of agents with heterogeneous goals deciding when to cooperate or act alone by introducing a hierarchical learning framework that combines imitation and reinforcement learning, demonstrating superior performance over baselines and revealing that modeling teammates is most beneficial when their goals are less observable.

Max Taylor-Davies, Neil Bramley, Christopher G. Lucas2026-03-10💻 cs

Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning

This paper introduces VASR, a multimodal reasoning framework for Context-Aware Visual Speech Recognition (CAVSR) that leverages an Audio-Visual Chain-of-Thought (AV-CoT) to explicitly ground acoustic signals with rich visual context like scenes and on-screen text, thereby overcoming single-modality dominance and achieving state-of-the-art performance.

Wenjie Tian, Mingchen Shao, Bingshen Mu, Xuelong Geng, Chengyou Wang, Yujie Liao, Zhixian Zhao, Ziyu Zhang, Jingbin Hu, Mengqi Wei, Lei Xie2026-03-10💻 cs

Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving

This paper proposes a kinematics-aware latent world model that integrates vehicle kinematic information and geometry-aware supervision into the Recurrent State-Space Model (RSSM) to enhance spatial representation and long-horizon imagination fidelity, thereby achieving more data-efficient and stable autonomous driving policy learning compared to existing baselines.

Jiazhuo Li, Linjiang Cao, Qi Liu, Xi Xiong2026-03-10💻 cs

Towards Network-Aware Operation of Integrated Energy Systems: A Comprehensive Review

This paper provides a comprehensive review of network-aware modeling, optimization, and control methods for Integrated Energy Systems, highlighting the critical role of network constraints in addressing operational challenges and outlining future research directions to achieve scalable, efficient, and low-carbon energy operations.

Alessandra Parisio2026-03-10💻 cs

How to Steal Reasoning Without Reasoning Traces

This paper introduces "trace inversion" models that can reconstruct detailed reasoning traces from only a target model's inputs, answers, and summaries, demonstrating that hiding reasoning chains fails to prevent the theft of reasoning capabilities and enabling significant performance gains for student models fine-tuned on these synthetic traces.

Tingwei Zhang, John X. Morris, Vitaly Shmatikov2026-03-10💻 cs

Sketch-Oriented Databases

This paper introduces sketch-oriented databases, a categorical framework that unifies various graph-based paradigms and features through finite-limit sketches, while proposing localizers for lazy path inference and stuttering sketches to enable modular composition and scalable model growth.

Dominique Duval, Rachid Echahed2026-03-10💻 cs

AutoDataset: A Lightweight System for Continuous Dataset Discovery and Search

AutoDataset is a lightweight, automated system that continuously monitors arXiv to detect, extract, and index newly released datasets from research papers, enabling real-time discovery and significantly improving search efficiency by up to 80%.

Junzhe Yang, Xinghao Chen, Yunuo Liu, Zhijing Sun, Wenjin Guo, Xiaoyu Shen2026-03-10💻 cs

VisualDeltas: Learning Preferences from Visual Quality Perturbations

VisualDeltas is a lightweight, label-free preference-learning framework that leverages systematic visual quality perturbations to generate informative supervision signals, thereby improving multimodal model performance and generalization without relying on human annotations.

Hailiang Huang, Yihao Liu, Shengyue Guan, Haoze Li, Sujian Li2026-03-10💻 cs

Worst--Case to Average--Case Reductions for SIS over integers

This paper establishes a worst-case to average-case reduction for a non-modular Short Integer Solution (SIS) problem over the integers, demonstrating that solving random instances of this problem efficiently allows for the polynomial-time approximation of the Shortest Independent Vectors Problem (SIVP) within a factor of $\widetilde{O}(n^{3/2})$ .

Konstantinos A. Draziotis, Myrto Eleftheria Gkogkou2026-03-10💻 cs

From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement

This paper presents a small-scale laboratory study demonstrating that embedding lightweight interactive components into Large Language Model-generated scaffolding can shift learners from passive consumption to active engagement, thereby improving perceived attention and short-term learning outcomes.

Zixin Chen, Haotian Li, Zhe Liu, Huamin Qu, Xing Xie2026-03-10💻 cs

← Previous Next →