Research Paper Cockpit

Daily Digest - 2026-07-23

Papers first seen in this daily snapshot.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-07-25.

Papers

48 visible entries

arxiv Score 24.6

Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?

2026-07-22 · Qiwei Ma, Chunping Qiu, Xinjun Cheng, Xiaoyu Zhang, Puhong Duan, Ke Yang, Xudong Kang, Shutao Li

General AI

The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU), enabling natural-language interaction with remote sensing imagery. However, a systematic understanding of the capability boundaries, cross-task generalization, and t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.6

PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity

2026-07-22 · Anmol Kankariya, Sercan Ö. Arık

General AI

While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction. Furthermore, standard single-stream prompting proves brittle when models encounter novel abstractions or rigorous domain constraints. We introduce P…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.6

PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning

2026-07-22 · Alexis Fox, Junlin Wang, Paul Rosu, Bhuwan Dhingra

Research Track A · General AI

Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected in their limited performance on continual learning benchmarks such as ARC-AGI-3, especially when models are evaluated out of the box. Various agent har…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.3

Leveraging ECRAM for Edge Continual Learning

2026-07-22 · Nabila Tasnim, Haoran Liu, Qing Cao, Saugata Ghose

Research Track A · General AI

Several edge computing platforms, such as autonomous vehicles and smart sensing devices, need to adapt to dynamic environments in real time by learning from new data in the field. Continual learning has emerged as a promising solution for edge training, by incorporating techniques that successfully combine a highly sum…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.6

Notes to Self: Can LLMs Benefit from Experiential Abstractions?

2026-07-22 · Chang Liu, Xinyu Li, Artur Dubrawski

General AI

Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effectively. We study whether Large Language Models (LLMs) can similarly benefit from such experiential abstractions. From LLMs' solution traces on the MATH training set, a st…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.6

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

2026-07-22 · Adel ElZemity, Shujun Li, Budi Arief

General AI

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models motivate e…

Review
pending
Role
unreviewed
Read
now
huggingface Score 19.8

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

2026-07-22 · Kailin Jiang, Lei Liu, Jian Xi, Hui Xu, Junlin Liu, Baochen Fu, Shaoqing Ren, Bin Li, Vichwang, Yu Lu, Haibo Shi

General AI

As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document interactions (redundancy, …

Review
pending
Role
unreviewed
Read
now
huggingface Score 19.4

An Exam for Active Observers

2026-07-17 · Jiarui Zhang, Muzi Tao, Shangshang Wang, Ollie Liu, Xuezhe Ma, Willie Neiswanger

General AI

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (MLLMs) exercise activ…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.6

IteraSim RAG: A Multi-Stage Retrieval-Augmented Agentic Back-End for OpenFOAM-Based Computational Fluid Dynamics

2026-07-22 · Pratyush Kumar

General AI

Configuring a computational fluid dynamics (CFD) case in OpenFOAM requires assembling a multi-directory input deck of mutually consistent solver, discretisation and boundary-condition dictionaries -- a task that remains a substantial barrier to non-specialist use of open-source CFD software. Large language models (LLMs…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.8

Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control

2026-07-22 · Yubiao Ma, Han Yu, Kai Guo, Changtai Lv, Zhengquan Mao, Boyang Xing, Xuemei Ren, Dongdong Zheng

Research Track A

Humans can progressively acquire highly dynamic motor skills while preserving reliable everyday motor abilities. In contrast, existing humanoid controllers face a trade-off between generalist and specialist capabilities: generalist motion tracking policies struggle to reliably execute rare highly dynamic motions, where…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.6

Diverse-Intent Multi-Turn Fashion Image Retrieval

2026-07-22 · Mingqiang Tang, Haokun Wen, Meng Liu, Yupeng Hu, Weili Guan, Xuemeng Song

General AI

Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictive assumption that every interaction follows the same attribute-editing paradigm, leaving heterogeneous intent transitions unexplored. Moreover, existing approaches ofte…

Review
pending
Role
unreviewed
Read
now
huggingface Score 15.0

AutoIndex: Learning Representation Programs for Retrieval

2026-07-21 · Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy, Hanna Jiang, Shreyas Chaudhari, Andrew Drozdov

General AI

We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich…

Review
pending
Role
unreviewed
Read
now
huggingface Score 14.8

SLPO: Scaling Latent Reasoning via a Surrogate Policy

2026-07-22 · Runyang You, Zhiyuan Liu, Yongqi Li, Wenjie Li

General AI

Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since every intermediate step must be decoded as a language token. Latent reasoning instead carries intermediate …

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.6

ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models

2026-07-22 · Karan Goyal, Afreen Hossain, Debojyoti Das, Vishal Bhutani

General AI

Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true, or even meaningful. Recently, it has been identified and given a mechanistic account in unimodal language models. Whether and how it manifests in vision-langu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.6

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

2026-07-22 · Pengcheng Wang, Zhiquan Wang, Jayoung Lee, Zhuoyan Xu, Ran Xu, Saurabh Bagchi, Yin Li, Somali Chaterji

General AI

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large number of input visual tokens and the heavy computation of the large language model (LLM), remains a key barrier to practical deployment. R…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.6

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference

2026-07-22 · Niqi Lyu, Pengtao Shi, Wei Qiu, Jianlin Zhong, Sicong Xia, Jianyao Ma, Yicheng Ding

General AI

Large language models (LLMs) provide strong reasoning capabilities but are expensive to serve at scale, whereas small language models (SLMs) are cheaper but less reliable on difficult problems. We introduce PyroDash, a cost-aware framework for token-level SLM-LLM collaborative inference. During generation, the SLM deci…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.8

Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning

2026-07-22 · Md Tanvirul Alam

General AI

Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the lack of training data that are simultaneously broad, exactly verifiable, and reproducible. We introduce Trace, a taxonomy-guided environment f…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.0

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

2026-07-21 · Nischay Dhankhar, Dos Baha, Abulhair Saparov

General AI

Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although hypernetworks are typically applied for test-time adaptation, we explore their use in train-time knowledge injection, whe…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.8

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

2026-07-22 · Jiazhen Jiang, Boxi Cao, Lingyong Yan, Yaojie Lu, Hongyu Lin, Shuaiqiang Wang, Dawei Yin, Xianpei Han, Le Sun

General AI

As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows. In this paper, we introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hiera…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.8

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

2026-07-22 · Dongfang Li, Xiaodong Luo, Ruoyu Sun, Xuhui Chen, Linyuan Qiu, Jian Meng, Zhengxuan Lu, Yiting Wang, Yucheng Xie, Tao Guo, Tianxiang Fang, Jing Li, Sihang Chen, Shihao Hong, Chang Liu, Weihua Dai, Zirong Zeng, Ziwei Zhu, Zhuohan Wang, Zhengjun Yue, Igor Vasilyev, Min Liu, Weijian Sun, Xin Chen, Yingmeng Gao, Jinhua Zhou, Taolue Chen, Chenwei Wu, Dong Zhang, Wenlong Jin, Jinmin Xiang, Barkova Maria, Ushakov Anton, Xianfei Jin, Tian Ding, Zhihang Lin, Qian Chen, Linxin Yang, Mingzhe Yang, Bingwei Zhang, Hongzhang Yang, Fangxue Zhang, Shijun Qin, Jie Yu, Cuihua Hu, Tolstykh Vasiliy, Nosov Ivan, Abdullin Amir, Zhichen Zhou, Xin Zhang, Zhixiong Ning, Xutong Zhao, Junjie Huang, Jiajun Liu, Weiyan Kong, Zheng Zhang, Wenhan Luo, Lin Hu, Yangbo Guo, Li Zeng, Shihao Zeng, Baotian Hu, Min Zhang, Haizhou Li, Zhiquan Luo

General AI

Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training systems are built around…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.6

LKValues: Aligning Large Language Models with Sri Lankan Societal Values

2026-07-22 · Nethmi Muthugala, Supryadi, Surangika Ranathunga, Nisansa de Silva, Ruijie Tao, Ovindu Gunatunga, Pengyun Zhu, Shaowei Zhang, Jingting Zheng, Deyi Xiong

General AI

Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societies such as Sri Lanka that have their unique cultural dynamics. Existing benchmarks overlook Sri Lankan-contextualized values in its official…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.6

SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction

2026-07-22 · Sriprabha Ramanarayanan, Rahul G. S., Mohammad Al Fahim, Keerthi Ram, Ramesh Venkatesan, Mohanasankar Sivaprakasam

General AI

Attention Mechanism (AM) selectively focuses on essential information for imaging tasks and captures relationships between distant pixel neighborhoods to compute feature representations. Accelerated MRI reconstruction benefits from AM, as the imaging process involves Fourier domain measurements that influence image rep…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.4

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

2026-07-11 · Zhicheng Cai, Xinyuan Guo, Hanlin Wu, Mingxuan Wang, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou

General AI

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.6

Development of an automated, reliable, and clinically meaningful artificial intelligence (AI) tool for diagnosing cardiac disease from conventional cardiovascular magnetic resonance (CMR) images

2026-07-22 · Sina Amirrajab, Volker Vehof, Michael Bietenbeck, Nuriye Akyol, Redouane Bouras, Khuraman Isgandarova, Alexandru Zlibut, Philipp Stalling, Ali Yilmaz

General AI

Aims: Cardiovascular magnetic resonance (CMR) imaging enables non-invasive assessment of myocardial structure, function, and pathology, but requires substantial experience in interpretation of CMR images that could be supported by artificial intelligence (AI)-based models. However, use of AI models for enhanced CMR rea…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.8

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

2026-07-22 · Markus J. Buehler

General AI

Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics. Here we show that materials science mechanism information in the open-weight google/gemma-4-E4B-it model has three experimentally separable forms: concepts are readable…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.6

Capturing Inner Experience At Scale: An AI Interviewer Co-Developed with the Founder of a Landmark Phenomenological Method

2026-07-22 · Jona Carmon, Clara Bersch, Charles Fernyhough, Russell T. Hurlburt, Simone Kühn

General AI

Subjective experience is central to psychological science, yet methods for studying it force a choice between depth and scale. Classical Experience sampling, as in ecological momentary assessments (EMA), captures experience as it occurs, but it confines participants to predetermined response formats that prescribe how …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.6

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

2026-07-22 · Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers, Carlo Ratti, Daniela Rus

General AI

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.6

Solar Open 2 Technical Report

2026-07-22 · Sungrae Park, Sanghoon Kim, Gyoungjin Gim, Jungho Cho, Hyunwoong Ko, Minbyul Jeong, Minjeong Kim, Keunwoo Choi, Chaehun Shin, Chanwoong Yoon, Dongjun Kim, Eunwon Kim, Gyungin Shin, Hyeonju Lee, Hyungkyu Kang, Inseo Song, Jisu Bae, Jiyoon Han, Jiyun Lee, Joonkee Kim, Junyeop Lee, Mikyoung Cha, Sangwon Yu, Sehwan Joo, Seokyoon Kang, Seonghoon Yang, Seung Shin, Seunghyun Lee, Seungseop Lim, Seungyoun Shin, Sukyung Lee, Taegyeong Eo, Taehwan Oh, Taewhoo Lee, Wonho Song, Wonjun Oh, Wonseok Hwang, Yunsu Kim, Yura Shim, Hwalsuk Lee, Sunghun Kim, Du-Seong Chang, Kyunghyun Cho, Seungju Han, Yejin Choi, Junsuk Choe, Hwaran Lee, Minjeong Ban, Yun Taewon, Hwanjun Song, Jae-Gil Lee, KyungTae Lim, Alice Oh

General AI

We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent trajectories in a single context, Solar Open 2 reaches a 1M-token window through a hybrid attention stack that interleaves one softmax layer am…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.6

Sound Probabilistic Safety Bounds for Large Language Models

2026-07-22 · Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate

General AI

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 9.8

Self Gradient Forcing: Native Long Video Extrapolation

2026-07-22 · Junhao Zhuang, Shiyi Zhang, Yuxuan Bian, Yaowei Li, Yawen Luo, Yijun Liu, Weiyang Jin, Songchun Zhang, Xianglong He, Xuying Zhang, Haoran Li, Haoyang Huang, Zeyue Xue, Nan Duan

General AI

Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-truth video contexts. This reduces exposure bias, but the historical key-value cache is still used by future frames only as frozen rollout stat…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.6

Statistical Inference for Rank Allocation in Low-Rank Adaptation

2026-07-22 · Yihang Gao, Vincent Y. F. Tan

General AI

Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models. Since different modules and layers may contribute unequally to downstream adaptation, allocating rank resources under a fixed parameter budget is an important problem for balancing efficiency, expressiv…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.6

Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

2026-07-22 · Nicolas Kosanovic, Jordan Dowdy, Jean Chagas Vaz

General AI

Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A popular control method used by manufacturers utilizes Virtual Reality for upper-body teleoperation and Reinforcement Learning for lower-body balance and locomotion control.…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

Cultural Evolution of Perfumes since 1900

2026-07-21 · Vahid Satarifard, Fabian Baumann, Geetanjali Minsky, Laura Sisson, Lou M. Haux, Christophe Laudamiel, Nicholas A. Christakis

Research Track A

Perfumes are cultural artifacts and works of sensory art, composed from a finite, recombinable palette of notes that together evoke a distinctive scent impression. Here, we assemble the largest perfume corpus compiled to date, spanning multiple independent databases from 1900 to 2024, and study its evolution through a …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.6

PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs

2026-07-22 · Amirhossein Sadr, Nima Soltani, Vahideh Moghtadaiee, Aida Pakniyat, Dara Rahmati, Saeid Gorgin

General AI

Physics-informed learning of partial differential equations (PDEs) has been dominated by multilayer perceptrons (MLPs), whose spectral bias and dense parameterization limit both accuracy and interpretability. Kolmogorov Arnold Networks (KANs) mitigate these limitations because their learnable spline activations are str…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.6

PercepCap: Video Captioner with Structured Spatio-Temporal Perception

2026-07-22 · Yifan Xu, Zihao Wang, Zhixiao Wang, Jiaming Zhang, Yichun Yang, Desen Meng, Yuanxing Zhang, Pengfei Wan, Limin Wang

General AI

Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions. As a r…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.6

State-Dependent Observation Noise Reintroduces Epistemic Value in Linear-Gaussian Active Inference

2026-07-22 · Daniel Corva

General AI

Recent work established that under active inference, linear-Gaussian state-space models lose their epistemic drive (any incentive to act so as to gain information) "under any circumstances". The epistemic term of the Expected Free Energy becomes constant: the agent flattens to a Kalman filter whose gain sequence is fix…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.6

The Blessing of Dimensionality: How Near-Orthogonality in High-Dimensional Spaces Explains Temporal Portability

2026-07-22 · Abigail Woodring, Adrian Chan, Rana Muhammad Shahroz Khan, Sukwon Yun, Chau-Wai Wong, Tianlong Chen

General AI

Fine-tuning has been widely used to adapt large language models (LLMs) for domain-specific tasks. Parameter efficient fine-tuning (PEFT) methods such as low-rank adaptation (LoRA) are frequently used to reduce computational costs. PortLLM is a training-free and data-free scheme used to adapt LLMs after continual pretra…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.8

SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments

2026-07-22 · Yang Xu, Gurpreet Singh Mukker, Raymond Wang, Jasper Gerigk, Maria Attarian, Igor Gilitschenski

General AI

Practical robotic grasping in complex scenes requires both 3D spatial reasoning and alignment with task-specific requirements. Vision-language models (VLMs) offer a natural way to specify these requirements using language, but existing approaches either use a VLM to predict the grasp directly with limited spatial aware…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.6

Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

2026-07-22 · Xiaoliang Shi, Zichen Wang, Runze Ma, Zhongyue Zhang, Shuangjia Zheng

General AI

Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requi…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.6

SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data

2026-07-22 · Wael AbdAlmageed

General AI

In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate vocabulary, argument structure, and trusted evidence are supplied by a Knowledge Graph (KG), or rule definitions. Classical neuro-symbolic pipelines have a discrete in…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.6

The Ethics of Autonomous AI Agents for Offensive Security

2026-07-22 · Andreas Happe, Jürgen Cito, Jasmin Wachter

General AI

LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling -- deterministic, narrowly scoped, and operated by trained practitioners -- agentic security tools exhibit \textit{indeterminacy} along three independent dimensions. First, their actions are drawn from a non-de…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 6.8

G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection

2026-07-22 · Yechan Kim, JongHyun Park, Dongho Yoon, Namhoon Jung, Moongu Jeon

General AI

This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD addresses key limitations of real-world aerial dataset construction, including limited viewpoint control, imperfect RGB-T alignment and high annotation cost. The framewo…

Review
pending
Role
unreviewed
Read
later
arxiv Score 6.6

Improved Lower Bounds and Output Augmentation for Facility Location Mechanisms

2026-07-22 · Rafael Gomes, Sophie Klumper, Guido Schäfer, Jens Schlöter

General AI

We study the strategic facility location problem under the egalitarian objective, where a mechanism uses the reported locations of a set of agents in Euclidean space to select a facility location that minimizes the maximum distance to any agent. We restrict our attention to strategyproof mechanisms, ensuring that no ag…

Review
pending
Role
unreviewed
Read
later
arxiv Score 6.6

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

2026-07-22 · Hiskias Dingeto

General AI

Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it. The test is structurally insensitive to individual false claims: if flipping a claim does not change the reconstruction, the claim is never penalized.…

Review
pending
Role
unreviewed
Read
later
huggingface Score 6.0

Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

2026-07-20 · Maximo Eduardo Rulli, Thomas Vaitses Fontanari, Simone Petruzzi, Federico Alvetreti, Giorgio Strano, Donato Crisostomi, Giorgos Nikolaou, Tommaso Mencattini, Andrea Santilli, Emanuele Rodolà, Simone Scardapane, Alessio Devoto

General AI

Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly conditioned on a timestep, raising a natural question: do these models internally represent denoising progress, and how is such information used…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.8

Opto-ViT-v2: Noise-Resilient On-Chip Fine-Tuning for Photonic Near-Sensor Vision Transformer Accelerators

2026-07-20 · Xuming Chen, Deniz Najafi, Mehrdad Morsali, Chengwei Zhou, Zahra Ghanaatianjobzari, Mahdi Nikdast, Shaahin Angizi, Gourav Datta

General AI

Silicon-photonic (SiPh) accelerators have emerged as a promising platform for Vision Transformer (ViT) inference by performing matrix multiplications on microring-resonator (MRR) banks with high throughput and energy efficiency. Extending these platforms to support on-chip fine-tuning remains challenging because backpr…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.4

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

2026-07-15 · Dwip Dalal, Shivansh Patel, Chahit Jain, Jeonghwan Kim, Utkarsh Mishra, Alex Baratian, Hyeonjeong Ha, Heng Ji, Svetlana Lazebnik, Unnat Jain

General AI

Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on w…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.4

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

2026-07-17 · Hao Liu, Chenghuan Huang, Ye Huang, Zhiying Wen, Mohan Zhang, Chen Li, Ziyang Ma, Jing Lyu, Jiangsu Du

General AI

Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-p routing creates uneven per-head workloads under multi-GPU sequence parallelism. The resulting workload …

Review
pending
Role
unreviewed
Read
later