Carlos's Debrief

May 3, 2026 09:00
46ArXiv Papers
11Web Findings
57Total Sources
Topics searched: Artificial Intelligence Machine Learning Large Language Models Security & Cybersecurity Cryptography Zero Knowledge Quantum Computing Crypto & Blockchain AI Agents & Reasoning AI Safety & Alignment
May 3, 2026 09:00 — Curated by Hermes Research Scout

⚡ Quick Summary

📰 News Headlines

🧠 LLMs 3

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation [17]
Xin Zhou, Dingkang Liang, Xiwu Chen, Feiyang Tan, Dingyuan Zhang, Hengshuang Zhao, Xiang Bai
Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models…
cs.CV
Chemical Taxonomy of $ω$~Centauri: Ten Populations Reveal a Multi-Phase Enrichment History [18]
Furkan Akbaba, Olcay Plevne, Timur Şahin, Sena Aleyna Şentürk
$ω$~Centauri, the most massive globular cluster in the Milky Way, exhibits a level of stellar population complexity that has long resisted a unified chemical characterisation. We exploit high-resolution near-infrared spectroscopy from the Milky Way Mapper…
astro-ph.GA
Representation Fréchet Loss for Visual Generation [23]
Jiawei Yang, Zhengyang Geng, Xuan Ju, Yonglong Tian, Yue Wang
We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g…
cs.CV

⚙️ Machine Learning 14

Synthetic Computers at Scale for Long-Horizon Productivity Simulation [2]
Tao Ge, Baolin Peng, Hao Cheng, Jianfeng Gao
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity…
cs.AI cs.CL cs.LG
LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis [3]
Lincan Li, Zheng Chen, Yushun Dong
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether correlation-based or learning-based, often generate redundant or irrelevant edges due to the…
cs.AI
PhyCo: Learning Controllable Physical Priors for Generative Motion [4]
Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan, Manmohan Chandraker
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces…
cs.CV cs.AI cs.LG
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists [5]
Yujun Wu, Dongxu Zhang, Xinchen Li, Jinhang Xu, Yiling Duan, Yumou Liu, Jiabao Pan, Xuanhe Zhou, Jingxuan Wei, Siyuan Li, Jintao Chen, Conghui He, Cheng Tan
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge…
cs.AI
An adaptive wavelet-based PINN for problems with localized high-magnitude source [12]
Himanshu Pandey, Ratikanta Behera
In recent years, physics-informed neural networks (PINNs) have gained significant attention for solving differential equations, although they suffer from two fundamental limitations, namely, spectral bias inherent in neural networks and loss imbalance arising from multiscale…
cs.LG
Strait: Perceiving Priority and Interference in ML Inference Serving [14]
Haidong Zhao, Nikolaos Georgantas
Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization and insufficient latency estimation under concurrent execution may restrict…
cs.LG
Mapping the Phase Diagram of the Vicsek Model with Machine Learning [15]
Grace T. Bai, Brandon B. Le
In this study, we use machine learning to classify and interpolate the phase structure of the Vicsek flocking model across the three-dimensional parameter space $(η,ρ,v_0)$. We construct a dataset of simulated parameter points and characterize…
cond-mat.soft cs.LG
Sequential Inference for Gaussian Processes: A Signal Processing Perspective [16]
Daniel Waxman, Fernando Llorente, Petar M. Djurić
The proliferation of capable and efficient machine learning (ML) models marks one of the strongest methodological shifts in signal processing (SP) in its nearly 100-year history. ML models support the development of SP systems that…
eess.SP cs.LG stat.CO stat.ML
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling [37]
Keming Wu, Zuhao Yang, Kaichen Zhang, Shizun Wang, Haowei Zhu, Sicong Leng, Zhongyu Yang, Qijie Wang, Sudong Wang, Ziting Wang, Zili Wang, Hui Zhang, Haonan Wang, Hang Zhou, Yifan Pu, Xingxuan Li, Fangneng Zhan, Bo Li, Lidong Bing, Yuxin Song, Ziwei Liu, Wenhu Chen, Jingdong Wang, Xinchao Wang, Xiaojuan Qi, Shijian Lu, Bin Wang
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field…
cs.CV
Intrinsic anomalous thermal hall effect as a signature of quantum metric in d-wave altermagnets [40]
Rishi G. Gopalakrishnan, Srimayi Korrapati, Sumanta Tewari
We investigate the intrinsic anomalous thermal Hall effect in d-wave altermagnets, where a transverse heat current is generated by a longitudinal temperature gradient in the absence of a magnetic field, with the leading response proportional…
cond-mat.mes-hall
Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy [41]
Andrea Dunn Beltran, Daniel Rho, Aarav Mehta, Xinqi Xiong, Raúl San José Estépar, Ron Alterovitz, Marc Niethammer, Roni Sengupta
Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is mitigated through breath-hold…
cs.CV
Machine Learning and Molecular Simulations Reveal Mechanisms of ZIFs Polymorph Selection [42]
Emilio Méndez, Rocio Semino
Zn(imidazolate)$_2$ metal-organic frameworks (MOFs) exhibit a remarkable degree of polymorphism. Because of their promising industrial applications, many research groups have investigated phase transitions, phase diagram and relative stability of these polymorphs. There is now wide…
cond-mat.mtrl-sci physics.chem-ph
AesRM: Improving Video Aesthetics with Expert-Level Feedback [44]
Yujin Han, Yujie Wei, Yefei He, Xinyu Liu, Tianle Li, Zichao Yu, Andi Han, Shiwei Zhang, Tingyu Weng, Difan Zou
Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyond visual fidelity. Prior work on visual aesthetics largely focuses on images, often reducing…
cs.CV
Akita: A High Usability Simulation Framework for Computer Architecture [45]
Sabila Al Jannat, Ying Li, Mengyang He, Xuzhong Wang, Huizhi Zhao, Jingxiang Sun, Daoxuan Xu, Enze Xu, Yifan Sun
Computer architecture simulation is essential for evaluating new designs without the need for costly tapeout. The community has developed dozens of valuable simulators that have enabled significant architectural advances. However, using and developing simulators remains…
cs.DC

🔒 Security & Crypto 12

Normativity and Productivism: Ableist Intelligence? A Degrowth Analysis of AI Sign Language Translation Tools for Deaf People [10]
Nina Seron-Abouelfadil, Poppy Fynes
Sign languages, of any geographical or accentual variation, understandably face continuous scrutiny under the ever present popularity of verbal dictation and audism. Through this, many potential problems arise with the current lack of accessible communication…
cs.AI cs.CY cs.HC
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption [25]
Yanting Wang, Chenlong Yin, Ying Chen, Jinyuan Jia
Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, and AI assistants. However, security remains a major concern for their widespread deployment…
cs.CR
TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [26]
Bowen Sun, Chaozhuo Li, Yaodong Yang, Yiwei Wang, Chaowei Xiao
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In real-world deployments, LLMs…
cs.CR cs.CL cs.LG
WOOTdroid: Whole-system Online On-device Tracing for Android [27]
Simon Althaus, Nikolaos Alexopoulos, Max Mühlhäuser, Christian Reuter, Ephraim Zimmer
System auditing on Android faces two problems. First, existing syscall tracers lose events under load, silently overwriting entries faster than a user space reader can drain them. Second, security-relevant application behavior is mediated through Binder…
cs.CR
Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures [29]
Ishrak Hamim Mahi, Siam Ferdous, Md Sakib Sadman Badhon, Nabid Hasan Omi, Md Habibun Nabi Hemel, Farig Yousuf Sadeque, Md. Tanzim Reza
The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology companies increasingly rely on…
cs.CV cs.CR cs.LG
Variational and Majorization Principles in Lattice Reduction [30]
Javier Blanco-Romero, Florina Almenares Mendoza
Lattice reduction smooths the Gram-Schmidt profile, and we use majorization to describe the local swap mechanism behind that smoothing. In this language, each non-degenerate Lovász swap acts as a T-transform on the log-norm profile. As…
cs.CR cs.DS
How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection [31]
Maofei Chen, Laifu Wang, Yue Qin, Yuan Wang, Bo Wu, Dongxin Liu
How code representation format shapes false positive behaviour in cross-language LLM vulnerability detection remains poorly understood. We systematically vary training intensity and code representation format, comparing raw source text with pruned Abstract Syntax Trees at…
cs.CR cs.SE
On the free Banach lattice generated by a lattice [32]
Asma Ben Rjeb, Pedro Tradacete
We study structural properties of the free Banach lattice $FBL\langle L\rangle$ generated by a distributive lattice $L$. We characterize when $FBL\langle L\rangle$ has a strong unit, compute its density character, analyze the density character of…
math.FA
Libra: Accelerating Socket I/O via Programmable Selective Data Copying [33]
Kairui Zhou, Shengkai Lin, Wei Zhang, Shizhen Zhao
Layer-7 (L7) proxies are critical to modern cloud-native systems, yet their performance is increasingly bottlenecked by copying entire payloads across the kernel-user boundary. Existing approaches reduce this overhead but typically sacrifice compatibility with unmodified POSIX…
cs.NI
Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling [34]
Gaurang Sharma, Juha Pajula, Aada Illikainen, Markus Rautell, Noora Lipsonen, Petri Alhainen, Mika Hilvo
Protecting sensitive health data while enabling collaborative analysis is a central challenge in healthcare. Traditional machine learning (ML) requires institutions to pool anonymized patient records, centralizing analytical development and privacy risks at a single site…
cs.LG
SBN Explorer: An Empirical Study of Cryptographic Boolean Networks [35]
Arnaud Valence
Boolean circuits form the foundational computational substrate of symmetric cryptography, yet the exploration of their architectural design space has remained largely confined to a handful of canonical paradigms - SPN, Feistel networks, and their immediate…
cs.CR
$\mathbb{K}$-framings and $\mathbb{K}$-quadratic forms on surfaces [36]
Nariya Kawazumi
We introduce the notions of $\mathbb{K}$-framings, based $\mathbb{K}$-framings and relative $\mathbb{K}$-framings of a compact connected oriented surface $Σ$ for any commutative ring $\mathbb{K}$ with unit, and a map which maps a based loop on $Σ$…
math.GT math.AT

🔐 Zero Knowledge 2

Computing Equilibrium beyond Unilateral Deviation [1]
Mingyang Liu, Gabriele Farina, Asuman Ozdaglar
Most familiar equilibrium concepts, such as Nash and correlated equilibrium, guarantee only that no single player can improve their utility by deviating unilaterally. They offer no guarantees against profitable coordinated deviations by coalitions. Although the…
cs.GT cs.AI cs.CC cs.LG
The hat and plus version of the Heegaard Floer contact invariant are not equivalent [38]
Alberto Cavallo, Irena Matkovič
We advance Matkovič ideas, originally applied to complete the classification of tight structures on small Seifert fibred $L$-spaces, to show the existence of contact structures on Brieskorn spheres which are tight and zero-twisting. This uncovers…
math.GT

⚛️ Quantum 6

Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders [13]
Emma Andrews, Sahan Sanjaya, Prabhat Mishra
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make…
quant-ph cs.LG
Covariant Locally Localized Gravity and vDVZ Continuity [20]
Hao Geng, Moritz Merz, Lisa Randall
The Karch-Randall braneworld concerns the physics of an AdS$_{d}$ brane embedded in an ambient gravitational AdS$_{d+1}$ spacetime. The gravitational theory induced on the AdS$_{d}$ brane has a very light but massive graviton. It has been…
hep-th gr-qc hep-ph
Observation of Vinen turbulence during far-from-equilibrium Bose-Einstein condensation [21]
Sebastian J. Morris, Martin Gazo, Simon M. Fischer, Haoyu Zhang, Christopher J. Ho, Nigel R. Cooper, Christoph Eigen, Zoran Hadzibabic
Relaxation of far-from-equilibrium quantum fluids, intimately related to the emergence of long-range order, is theoretically associated with the decay of a turbulent isotropic tangle of vortex lines. We observe and study such decaying quantum turbulence…
cond-mat.quant-gas cond-mat.other cond-mat.stat-mech quant-ph
Towards Systematics of Calabi-Yau Landscape for String Cosmology [24]
George K. Leontaris, Pramod Shukla
In this review, we discuss the relevance and impact of studying Calabi-Yau threefolds in the context of global model building in string phenomenology. First, taking a phenomenologist-friendly approach, we review how the topologies of the…
hep-th hep-ph
Cosmology of fractional gravity [39]
Iván Salvador-García, Gianluca Calcagni
This is a first study of the cosmology of classical fractional gravity, a nonlocal proposal endowed with self-adjoint fractional d'Alembertian operators which serves as the basis for an ultraviolet-complete theory of quantum gravity. We derive…
gr-qc hep-th
Source-independent quantum key distribution without pre-sending entanglement [43]
Rong-Zheng Liu, Hua-Lei Yin
Quantum key distribution (QKD) theoretically offers information-theoretic security. The prevailing approach is the prepare-and-measure BB84 protocol, which implements QKD using conventional laser rather than single-photon source via the decoy-state method. However, side-channel attacks targeting sources…
quant-ph

🛡️ AI Safety 4

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection [9]
Prashant Kulkarni
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature in the model's…
cs.CR cs.AI
Exploration Hacking: Can LLMs Learn to Resist RL Training? [11]
Eyon Jang, Damon Falck, Joschka Braun, Nathalie Kirch, Achu Menon, Perusha Moodley, Scott Emmons, Roland S. Zimmermann, David Lindner
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during training, which…
cs.LG cs.CL
MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks [28]
Jona te Lintelo, Lichao Wu, Marina Krček, Sengim Karayalçin, Stjepan Picek
Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradigm also introduces new safety challenges. Since only a subset of experts is engaged for…
cs.CR
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images [46]
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing…
cs.CV cs.CY

🤖 Agents 5

FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems [6]
Binghao Huang, Yunzhu Li
We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a practical "plug-in" module consisting of (i) thin, flexible tactile sensor pads that provide dense tactile signals…
cs.RO cs.AI cs.LG
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [7]
Chenxin Li, Zhengyang Tang, Huangxin Lin, Yunlong Lin, Shijue Huang, Shengyuan Liu, Bowen Ye, Rang Li, Lei Li, Benyou Wang, Yixuan Yuan
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final…
cs.SE cs.AI
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes [8]
Tianyuan Wu, Chaokun Chang, Lunxi Cao, Wei Gao, Wei Wang
Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching, and safe…
cs.OS cs.AI
OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction [19]
Junyoung Lee, Sookwan Han, Jeonghwan Kim, Inhee Lee, Mingi Choi, Jisoo Kim, Wonjung Woo, Hanbyul Joo
Human-robot collaboration has been studied primarily in dyadic or sequential settings. However, real homes require multiadic collaboration, where multiple humans and robots share a workspace, acting concurrently on interleaved subtasks with tight spatial and temporal…
cs.RO cs.CV
LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models [22]
Hao Chen, Jiaming Liu, Zhonghao Yan, Nuowei Han, Renrui Zhang, Chenyang Gu, Jialin Gao, Ziyu Guo, Siyuan Qian, Yinxi Wang, Peng Jia, Chi-Wing Fu, Shanghang Zhang, Pheng-Ann Heng
Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches share a critical limitation: whether employing explicit linguistic reasoning that suffers from latency and discretization, or utilizing more expressive continuous…
cs.RO cs.CV

🍟 Lobste.rs 2

Blocking Copy Fail (CVE-2026-31431) in Kubernetes with Tetragon [47]
Lobste.rs
A 732-byte Python script roots every Linux distro since 2017. Kernel patches are still rolling out. Here is how to block it at the syscall level with Tetragon and 22 lines of YAML.
Lobste.rs
ChatGPT Won't Let You Type Until Cloudflare Reads Your React State. I Decrypted the Program That Does It [48]
Lobste.rs
Edit April 2, 2026: I've been getting inbound interest from researchers wanting to run their own queries. The MCP integration I use for my own research lets you analyze live mobile telemetry continuously collected from…
Lobste.rs

🌐 HuggingFace papers 3

Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost [49]
HuggingFace papers
Commercial TTS systems produce near-native Indic audio, but the best open-source bases (Chatterbox, Indic Parler-TTS, IndicF5) trail them on measured phonological dimensions, and the most widely adopted multilingual base (Chatterbox, 23 languages) does not even…
HuggingFace papers
FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing [50]
HuggingFace papers
Fashion AI systems routinely encode the aesthetic logic of specific houses, editors, and historical moments without disclosing it. We present FASH-iCNN, a multimodal system trained on 87,547 Vogue runway images across 15 fashion houses spanning…
HuggingFace papers
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think [51]
HuggingFace papers
Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is hindered by the intractable likelihoods of…
HuggingFace papers

📚 google scholar 6

Early identification of breakthrough technologies: Insights from science-driven innovations [52]
google scholar
Early identification of breakthrough technologies: Insights from science-driven innovations
google scholar
Catalyst breakthroughs in methane dry reforming: Employing machine learning for future advancements [53]
google scholar
Catalyst breakthroughs in methane dry reforming: Employing machine learning for future advancements
google scholar
Large language models (LLM) in computational social science: prospects, current state, and challenges [54]
google scholar
Large language models (LLM) in computational social science: prospects, current state, and challenges
google scholar
Artificial intelligence and machine learning in cybersecurity: a deep dive into state-of-the-art techniques and future paradigms [55]
google scholar
Artificial intelligence and machine learning in cybersecurity: a deep dive into state-of-the-art techniques and future paradigms
google scholar
Securing the future: exploring post-quantum cryptography for authentication and user privacy in IoT devices [56]
google scholar
Cluster Computing - With the emergence of quantum computers, traditional cryptographic methods are vulnerable to attacks, emphasizing the need for post-quantum cryptography to secure devices and...
google scholar
Quantum machine learning: A comprehensive review of integrating AI with quantum computing for computational advancements [57]
google scholar
Quantum machine learning: A comprehensive review of integrating AI with quantum computing for computational advancements
google scholar

🔗 All Sources

  1. Computing Equilibrium beyond Unilateral Deviation
  2. Synthetic Computers at Scale for Long-Horizon Productivity Simulation
  3. LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
  4. PhyCo: Learning Controllable Physical Priors for Generative Motion
  5. Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
  6. FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems
  7. Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
  8. Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
  9. Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
  10. Normativity and Productivism: Ableist Intelligence? A Degrowth Analysis of AI Sign Language Translation Tools for Deaf People
  11. Exploration Hacking: Can LLMs Learn to Resist RL Training?
  12. An adaptive wavelet-based PINN for problems with localized high-magnitude source
  13. Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
  14. Strait: Perceiving Priority and Interference in ML Inference Serving
  15. Mapping the Phase Diagram of the Vicsek Model with Machine Learning
  16. Sequential Inference for Gaussian Processes: A Signal Processing Perspective
  17. HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
  18. Chemical Taxonomy of $ω$~Centauri: Ten Populations Reveal a Multi-Phase Enrichment History
  19. OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
  20. Covariant Locally Localized Gravity and vDVZ Continuity
  21. Observation of Vinen turbulence during far-from-equilibrium Bose-Einstein condensation
  22. LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models
  23. Representation Fréchet Loss for Visual Generation
  24. Towards Systematics of Calabi-Yau Landscape for String Cosmology
  25. FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
  26. TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
  27. WOOTdroid: Whole-system Online On-device Tracing for Android
  28. MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
  29. Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures
  1. Variational and Majorization Principles in Lattice Reduction
  2. How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
  3. On the free Banach lattice generated by a lattice
  4. Libra: Accelerating Socket I/O via Programmable Selective Data Copying
  5. Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling
  6. SBN Explorer: An Empirical Study of Cryptographic Boolean Networks
  7. $\mathbb{K}$-framings and $\mathbb{K}$-quadratic forms on surfaces
  8. Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
  9. The hat and plus version of the Heegaard Floer contact invariant are not equivalent
  10. Cosmology of fractional gravity
  11. Intrinsic anomalous thermal hall effect as a signature of quantum metric in d-wave altermagnets
  12. Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy
  13. Machine Learning and Molecular Simulations Reveal Mechanisms of ZIFs Polymorph Selection
  14. Source-independent quantum key distribution without pre-sending entanglement
  15. AesRM: Improving Video Aesthetics with Expert-Level Feedback
  16. Akita: A High Usability Simulation Framework for Computer Architecture
  17. AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images
  18. Blocking Copy Fail (CVE-2026-31431) in Kubernetes with Tetragon
  19. ChatGPT Won't Let You Type Until Cloudflare Reads Your React State. I Decrypted the Program That Does It
  20. Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
  21. FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing
  22. V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
  23. Early identification of breakthrough technologies: Insights from science-driven innovations
  24. Catalyst breakthroughs in methane dry reforming: Employing machine learning for future advancements
  25. Large language models (LLM) in computational social science: prospects, current state, and challenges
  26. Artificial intelligence and machine learning in cybersecurity: a deep dive into state-of-the-art techniques and future paradigms
  27. Securing the future: exploring post-quantum cryptography for authentication and user privacy in IoT devices
  28. Quantum machine learning: A comprehensive review of integrating AI with quantum computing for computational advancements
Generated by Hermes Agent • arXiv • Google Scholar • Lobste.rs • Hacker News • HuggingFace