cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5153, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

25
EverydayBench: Evaluating Satisfactory Completion of Live User-Facing Digital Work
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25146v1 Announce Type: new Abstract: Everyday digital tasks, from selecting products and planning trips to conducting research and creating artifacts, require AI agents to deliver useful outcomes rather than merely retrieve web information. Yet evaluating these outcom…

🅲 hạng C
25
A Verifier from the Past: Test-Time Compute for Time Series Foundation Models
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25171v1 Announce Type: new Abstract: Test-time compute (TTC) improves language models by spending additional inference compute to generate, verify, and select among candidate outputs, but this recipe has not transferred directly to time series forecasting. A language …

🅲 hạng C
25
Steering Automated Scientific Discovery via Audited Epistemic Exploration
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25214v1 Announce Type: new Abstract: Scientific discovery requires revisiting the hypotheses in light of new evidence and identifying promising directions beyond those already explored. However, research agents often make claims that are not supported by their observa…

🅲 hạng C
25
A Neurosymbolic Multimodal Framework for 30-Day Diabetic Readmission Prediction: Integrating Structured EHR Data, Dense Clinical Embeddings, and Knowledge-Grounded Symbolic Extraction
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25236v1 Announce Type: new Abstract: Unplanned 30-day readmissions among patients with diabetes mellitus impose a substantial clinical and economic burden, yet most predictive models use only structured electronic health record (EHR) data and ignore free-text clinical…

🅲 hạng C
25
MS-Point: Multi-Modal Hierarchical Spectral Learning for Point Cloud Understanding
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25282v1 Announce Type: new Abstract: Point-image alignment learns useful object representations, but different local feature patterns can produce the same pooled descriptor and receive the same alignment signal. We introduce MS-Point, a cross-modal pretraining framewo…

🅲 hạng C
25
Falsifiable Compositional Reasoning in Time Series Forecasting
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25388v1 Announce Type: new Abstract: Time series foundation models as well as the language-guided analytical agents achieve strong accuracy on standard chronological benchmarks. However, models that rank highest on historical validation splits often degrade across non…

🅲 hạng C
25
The Coevolution and Coexistence of Humans and AI
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25393v1 Announce Type: new Abstract: Artificial intelligence (AI) systems replicate through deployment, vary through training, and compete for computational resources. These processes create the conditions for natural selection and raise a fundamental question: will A…

🅲 hạng C
25
LoongForge-Embodied: A Unified Framework for Training Heterogeneous Embodied Models
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25460v1 Announce Type: new Abstract: Training Vision-Language-Action (VLA) models and World-Action Models (WAMs) is computationally expensive, while their heterogeneous architectures and fragmented training stacks make system optimizations difficult to reuse across mo…

🅲 hạng C
25
Coordinated Use of Large Language Models in Academic Research
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25502v1 Announce Type: new Abstract: This study proposes a methodological framework for the coordinated use of multiple large language models in academic research. Its central argument is that involving more models does not in itself guarantee more reliable results; w…

🅲 hạng C
25
Keystone: Judging Previews at Key Steps for Test-Time Search in Diffusion Models
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25530v1 Announce Type: new Abstract: Text-to-image diffusion and flow models yield a preview, their clean-image estimate, at every denoising step. When they miscount, drop or misplace objects, test-time search is in a bind: its verifiers are reward models built for fi…

🅲 hạng C
25
Efficient Multimodal Agents for Auditing 3D Worlds
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25543v1 Announce Type: new Abstract: Multimodal agents can now build interactive 3D worlds and games, yet these worlds, like those built by people, often contain glitches such as floating objects, walls that can be walked through, or objects that change when no one is…

🅲 hạng C
25
AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25568v1 Announce Type: new Abstract: Aerial sensing must combine uncertain overhead context with current observations while budgeting prediction, movement and image processing. AeroBelief uses the next executable action as the unit of verification against reference sc…

🅲 hạng C
25
Learning Networked Dynamical Systems via Neural ODE-based Graph Structure Inference
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25586v1 Announce Type: new Abstract: Inferring the latent interaction graph from multivariate time series is fundamental to understanding complex dynamical systems in neuroscience, biology, and physics. Despite recent progress in neural relational inference, most meth…

🅲 hạng C
25
Don't Lose the Future: Latent-Aware 4-Bit Quantization of World Action Models
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.25614v1 Announce Type: new Abstract: World action models (WAMs) predict how a scene will evolve and condition their actions on this predicted future. Deploying them on a robot's onboard computer calls for 4-bit weights, activations and key-value caches (W4A4KV4). Exis…

🅲 hạng C
25
Mutable State in Enrich-by-Need Security Protocol Analysis
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25142v1 Announce Type: new Abstract: Security protocol analysis has emphasized message-passing, as this is how different principals interact in authentication, key exchange, and similar functionalities. However, in many protocols a principal also maintains mutable sta…

🅲 hạng C
25
User Perceptions of Deceptive In-Vehicle Infotainment User Interfaces
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25195v1 Announce Type: new Abstract: Modern vehicles collect extensive data about drivers, passengers, and vehicle use, with privacy and consent decisions increasingly mediated through infotainment software. Although dark patterns have been widely studied in web, mobi…

🅲 hạng C
25
Release-Bound Withdrawal Authorization for Bitcoin Custody
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25231v1 Announce Type: new Abstract: A compromised cryptocurrency withdrawal backend can request signatures on unauthorized payments. Previously signed transactions may remain spendable after pause or become spendable again after a reorganization. Release-Bound Withdr…

🅲 hạng C
25
VisualJevBench: A Benchmark and Black-Box Attacks for Visual Typed Decision Models
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25435v1 Announce Type: new Abstract: Typed decision models (TDMs) return structured decisions instead of generating free-text responses, enabling fast and cheap decisions in real-world applications. Recent support for image inputs extends Jev, a representative TDM, to…

🅲 hạng C
25
LingSante MedGuard Technical Report
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25509v1 Announce Type: new Abstract: As medical AI is increasingly used for patient consultation and clinical decision support, identifying harmful, non-compliant, or ethically problematic responses is essential for responsible deployment. Assessing these risks requir…

🅲 hạng C
25
GPU-Accelerated Secure Inference for Drug--Target Interaction Prediction
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25664v1 Announce Type: new Abstract: Deep learning models that predict drug--target interactions (DTI) can speed up drug discovery, but the candidate drugs they score are valuable intellectual property that their owners cannot reveal. Secure multiparty computation (MP…

🅲 hạng C
25
Question, Then Affirm: Restoring Commitment Does Not Restore Refusal
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.25929v1 Announce Type: new Abstract: We find that safeguards for image generation can be bypassed without changing what a message says. A sign stating a harmful proposition is blocked, but the same proposition phrased as a question and followed by a check mark is gene…

🅲 hạng C
25
Causal Overtaking in Fair Transaction Ordering
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.26100v1 Announce Type: new Abstract: Fair transaction ordering protocols aim to mitigate front-running using replica-local arrival orders, but prior work often assumes a single submission origin for each responsive transaction. We identify causal overtaking, in which …

🅲 hạng C
25
ChronoPatch: Black-Box Energy-Latency Attacks on Vision-Language Models
📄 Paper arXiv cs.CR 5 giờ trước

arXiv:2611.26117v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed as generative inference services, where autoregressive decoding makes response length a key determinant of latency and computational cost. This creates an availability risk: a…

🅲 hạng C
25
Samiksa
🛠️ Công cụ AI Product Hunt 5 giờ trước

Understand research, test it yourself, publish your own Discussion | Link

🅲 hạng C
25
Interview Coach
🛠️ Công cụ AI Product Hunt 6 giờ trước

Practice job interviews out loud Discussion | Link

🅲 hạng C
24
Fack’d
🛠️ Công cụ AI Product Hunt 7 giờ trước

Fact checks right on YouTube as it plays, with sources Discussion | Link

🅲 hạng C