cập nhật 50 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.7 giờ sau khi CVE được công bố (n = 5162, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Pandora's Toolbox Or Why Agent Safety Cannot Be Verified
📄 Paper arXiv cs.AI 12 giờ trước

arXiv:2611.25325v1 Announce Type: new Abstract: Present artificial intelligence agents are constructed by means of a coupling between a fixed language model with a general computing device. We show that this coupling makes safety undecidable. In particular, we show that given so…

🅲 hạng C
26
Continual Tool-Space Extension Learning for Multimodal Agents
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.23810v1 Announce Type: new Abstract: Multimodal agents largely rely on generic tools such as cropping, search, and code execution, leaving specialist vision models outside their tool space. However, bringing such a model into an already trained agent is not straightfo…

🅲 hạng C
25
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming secu…

🅲 hạng C
25
Sage S2.1 Flash Technical Report
📄 Paper HF Daily Papers 4 ngày trước

We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents…

🅲 hạng C
24
A Reinforcement Learning Method to Navigate SMEFT Operator Space
📄 Paper HF Daily Papers 4 ngày trước

In particle physics, discrepancies between experimental measurements and Standard Model (SM) predictions are commonly interpreted within new theoretical models. In this context, the Standard Model Effective Field Theory (SMEFT) provides a general framework encompassing a broad cl…

🅲 hạng C
24
Steering Automated Scientific Discovery via Audited Epistemic Exploration
📄 Paper arXiv cs.AI 12 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
24
Mutable State in Enrich-by-Need Security Protocol Analysis
📄 Paper arXiv cs.CR 12 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
24
ChronoPatch: Black-Box Energy-Latency Attacks on Vision-Language Models
📄 Paper arXiv cs.CR 12 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
24
Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration
📄 Paper HF Daily Papers 2 ngày trước

NPU design-space exploration for LLM inference mainly relies on an expensive simulator that often returns only scalar feedback such as latency and power. Such feedback can rank evaluated configurations, but gives little information for deciding why a configuration is slow or whic…

🅲 hạng C
24
Weight-Space Programming Doesn't Need Transformers
📄 Paper HF Daily Papers 3 ngày trước

Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes target weights by hand without gradient-based training, so those reasons no longe…

🅲 hạng C
24
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights
📄 Paper HF Daily Papers 1 ngày trước

Pretrained language models (LMs) remain unreliable on exact multi-digit arithmetic without gradient fine-tuning or external tool interpreters. We introduce closed-form, zero-gradient circuit-grafting primitives that compile deterministic computation directly into pretrained LM we…

🅲 hạng C
23
HiUni: Harmonizing Understanding and Generation in Shared Visual Space
📄 Paper HF Daily Papers 1 ngày trước

Unified multimodal models aim to support visual understanding and generation within a single framework. However, prevailing approaches often separate their visual representations or backbone computation to accommodate the different requirements of these two tasks, which limits th…

🅲 hạng C
23
TuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAs
📄 Paper HF Daily Papers 1 ngày trước

Humans act in the visual world by inferring the 3D layout behind a 2D view, predicting how an action changes it, and correcting themselves after seeing the result. Can multimodal large language models (MLLMs) do the same? CAPTCHAs offer a natural test, since humans solve them thr…

🅲 hạng C
22
Training Vision Models for LLM-Driven Weight-Space Programming
📄 Paper HF Daily Papers 1 ngày trước

It has been demonstrated that, in certain settings, large language models can perform weight-space programming to directly modify the weights of neural networks. However, it is unknown how dedicated training of these networks can contribute to the successes of weight-space progra…

🅲 hạng C
22
Lossless Reversible Watermarking for AIGC with Applications in Authentication
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.23395v1 Announce Type: new Abstract: AIGC watermarking is commonly used for tracing, but it can also support applications such as authentication and tampering detection. We study lossless reversible watermarking, which enables exact recovery of the original watermarke…

🅲 hạng C
22
CurvDelta: Low-Curvature Delta Modeling For Surgical Learning and Unlearning
📄 Paper HF Daily Papers 2 ngày trước

A central challenge in adapting large language models (LLMs) is capability preservation: an adaptation can achieve its target while degrading general capabilities. We introduce CurvDelta, a scalable framework that incorporates the preservation constraint into the parameterization…

🅲 hạng C
22
WorldRuler: Interactive World Modeling under Configurable Rules
📄 Paper HF Daily Papers 2 ngày trước

Rules govern how player actions change interactive worlds. Different rules create distinct gameplay experiences within similar scenes and action spaces. For customizable gameplay, generative world models must follow user-defined rules beyond real-world behaviors. However, realizi…

🅲 hạng C
22
DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding
📄 Paper arXiv cs.AI 2 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.21925v1 Announce Type: new Abstract: Speculative-diffusion decoding uses a small parallel drafter model to generate b draft tokens in one forward pass, which then undergo parallel verification via a larger target model. Faster inference can be achieved when multiple d…

🅲 hạng C
21
Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain
📄 Paper HF Daily Papers 1 ngày trước

Native 3D generation has largely been built around latent diffusion, with recent advances concentrating on stronger variational autoencoders (VAE) and increasingly elaborate latent representations, from vecset and triplanes to structured sparse voxels. Despite their architectural…

🅲 hạng C
21
Fidelity Regret: Measuring Simulator Misspecification in Verifiable Design
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.22263v1 Announce Type: new Abstract: RLVF assumes the verifier evaluates the quantity of interest. In genetic-circuit design, a topological verifier can establish that a program is a valid circuit computing the target function, whereas ranking its physical performance…

🅲 hạng C
21
TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation
📄 Paper HF Daily Papers 3 ngày trước

Robot manipulation videos provide a rich visual experience, yet recovering robot action and gripper-state annotations from RGB observations still remains challenging. Using the embodiment-agnostic tool-center-point (TCP) pose as the action space, we present TCP4D, a unified model…

🅲 hạng C
21
UltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture Generation
📄 Paper HF Daily Papers 2 ngày trước

Generating physically based rendering (PBR) texture maps for a 3D mesh from a single reference image is highly ambiguous, as the observed appearance entangles material identity, surface reflectance, and illumination. While current generative methods produce realistic albedo maps,…

🅲 hạng C
21
π^4: A Foundation Model for 4D Scene Geometry and Motion
📄 Paper HF Daily Papers 3 ngày trước

π^4 is a unified foundation model for 4D scene perception. From diverse, uncalibrated RGB observations in the wild---a single image, an unordered collection, or a video sequence---it recovers dense geometry, camera poses, and metric scale, together with 2D/3D point tracks and mov…

🅲 hạng C
21
Recurrent Domain Incremental Adaptation of Time-Series Foundation Models
📄 Paper HF Daily Papers 2 ngày trước

Pretrained Time-Series Foundation Models (TSFMs) provide strong representations for downstream classification tasks. Yet adapting a TSFM under changing operating conditions remains challenging. A model must improve on each newly observed condition without sacrificing conditions i…

🅲 hạng C
20
Out of Sight, Still in Mind: Token Compression for Omni-LLMs
📄 Paper HF Daily Papers 3 ngày trước

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of …

🅲 hạng C