cập nhật 1 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5451, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

26
Modeling LLM Reasoning Dynamics with Structural Representations
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23749v1 Announce Type: new Abstract: Language-model reasoning alternates between sustained activities and local operations. We study how this temporal structure predicts continuation and the computation needed to analyze it. T/E/S combines text, local events, and span…

🅲 hạng C
26
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
📄 Paper arXiv cs.CR 11 giờ 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
26
STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.20765v1 Announce Type: new Abstract: Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically d…

🅲 hạng C
26
GuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based Recommendation
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.22274v1 Announce Type: cross Abstract: In traditional recommender systems (RSs), textual information typically serves as auxiliary signals for representation learning. In contrast, in LLM-based RSs, textual information becomes the primary medium for recommendation gen…

🅲 hạng C
25
Sage S2.1 Flash Technical Report
📄 Paper HF Daily Papers 3 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
25
MillBill: A Machining Agent with Geometric Feedback
📄 Paper HF Daily Papers 2 ngày trước

Turning a CAD model into a machining program requires both process knowledge and geometric precision. Language models can generate such workflows by writing geometry and toolpath code for each part, but this makes numerical execution part of the model's task. We introduce MillBil…

🅲 hạng C
24
BOS Summary: The First Token Matters
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standa…

🅲 hạng C
24
Erased but Recoverable: On the Fragility of Concept Erasure Under Fine-Tuning
📄 Paper arXiv cs.CR 11 giờ trước

arXiv:2611.24220v1 Announce Type: new Abstract: Existing concept erasure methods for text-to-image diffusion models primarily focus on suppressing target concepts while preserving non-target generation quality. However, in practical applications, open-source diffusion models are…

🅲 hạng C
24
Intent-Aware Protection for AI Agents
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine…

🅲 hạng C
24
Privacy-Preserving Clustering Algorithm and Parameter Selection for Collaborative Population Stratification Using Distributed PCA
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.18925v1 Announce Type: new Abstract: We propose a privacy-preserving selection layer for collaborative population stratification workflows, enabling an honest-but-curious server to recommend a strong clustering algorithm-hyperparameter configuration from privacy prote…

🅲 hạng C
23
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment
📄 Paper HF Daily Papers 3 ngày trước

Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment wi…

🅲 hạng C
23
VoxMel TTS Technical Report
📄 Paper HF Daily Papers 4 ngày trước

Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, t…

🅲 hạng C
23
Privacy Leakage from Recurrent State in LLM Inference
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.16048v1 Announce Type: new Abstract: Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent st…

🅲 hạng C
22
LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22131v1 Announce Type: new Abstract: Whole image embeddings can under represent small objects and local attributes that distinguish relevant images for localized queries. We present LoCaR, a training free framework for localized text to image retrieval with frozen vis…

🅲 hạng C
22
TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation
📄 Paper HF Daily Papers 2 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
Match and Correct: A Repeated Computational Motif in Evoformer Layers
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19016v1 Announce Type: new Abstract: Triangle attention and triangle multiplicative updates form key components of the Evoformer, and were introduced specifically to encourage consistency with the triangle inequality. Yet whether representational changes over layers r…

🅲 hạng C
21
ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters
📄 Paper HF Daily Papers 3 ngày trước

Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM …

🅲 hạng C
21
Recurrent Domain Incremental Adaptation of Time-Series Foundation Models
📄 Paper HF Daily Papers 1 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
21
AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data
📄 Paper HF Daily Papers 4 ngày trước

Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional p…

🅲 hạng C
21
BiCAT: Bimanual Coordination Action Tokenization
📄 Paper HF Daily Papers 2 ngày trước

Autoregressive vision-language-action (VLA) models predict discrete action tokens with the next-token objective of their vision-language backbone, so the action tokenizer defines the interface between the policy and the robot. In bimanual manipulation, the two arms share a repert…

🅲 hạng C
21
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…

🅲 hạng C
21
TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17781v1 Announce Type: new Abstract: When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves chang…

🅲 hạng C
21
Representational Geometry as a Diagnostic for Adversarial Robustness
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.17684v1 Announce Type: cross Abstract: Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network …

🅲 hạng C
21
Let Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view Consensus
📄 Paper HF Daily Papers 2 ngày trước

Deep models often rely on spurious correlations that fail on underrepresented groups. Existing methods either correct human-specified bias attributes or infer unknown biases from the learned representation space. However, annotated attributes may differ from the shortcuts actuall…

🅲 hạng C
20
GlyphAtlas: Disentangling Stroke Detail from Layout for Scene Text Synthesis
📄 Paper HF Daily Papers 4 ngày trước

Scene text synthesis requires stroke-accurate characters rendered in a specified layout, as well as visual coherence with the surrounding scene. To achieve this, existing methods commonly pre-render the target text at its intended locations to form a glyph image that jointly spec…

🅲 hạng C
20
Restoring Diversity in Distilled Image and Video Generators by Probing Activations
📄 Paper HF Daily Papers 6 ngày trước

Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe diversity collapse: samples generated from different random seeds show minimal variation. In this work, we investigate the root cause of this failure by probing the…

🅲 hạng C