cập nhật 8 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5481, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.19215v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionate…

🅲 hạng C
29
I2C-GRPO: Insight Importance Checklist for Reinforcement Learning in a Multi-Agent DDoS Alert Triage Workflow
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.17534v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for investigative tasks over incomplete evidence, such as cybersecurity alert triage, but reinforcement learning (RL) for such tasks is difficult: intermediate steps have no v…

🅲 hạng C
28
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
📄 Paper HF Daily Papers 5 ngày trước

Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a…

🅲 hạng C
25
Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution
📄 Paper arXiv cs.AI 5 ngày trước

Paper đề xuất 'tách quyền lực' (separation of powers) cho agentic program evolution với 3 vai trò: govern (điều hướng từ bằng chứng), propose (sinh ứng viên), judge (validate fitness). Thống kê thấy hệ thống controller-centric và agent-centric đều lệch bên và tổn phí tài nguyên khi agent tự làm cả hai. Tham khảo khi design kiến trúc evolution pipeline cho code agent.

🅲 hạng C
24
AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs
📄 Paper arXiv cs.AI 2 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to…

🅲 hạng C
24
Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
📄 Paper arXiv cs.AI 13 giờ trước

arXiv:2611.22174v1 Announce Type: new Abstract: General-purpose behavior models increasingly internalize broad procedural knowledge during training, making their adaptation to new goals and skill interfaces less a problem of learning entirely new behaviors than of reconfiguring …

🅲 hạng C
24
The Fragility of Reasoning-Importance Attribution for Pruning Language Models
📄 Paper arXiv cs.AI 13 giờ trước

arXiv:2611.22234v1 Announce Type: new Abstract: Attribution-guided pruning scores components by their causal contribution and protects the important ones, and it is increasingly applied to compress reasoning language models without destroying their chain of thought. Its reliabil…

🅲 hạng C
24
Wrong Input, Wrong Threshold: Re-evaluating Adversarial Facial Privacy
📄 Paper arXiv cs.CR 13 giờ trước

arXiv:2611.21923v1 Announce Type: cross Abstract: Published face-privacy methods report protection above 90% against black-box recognition models. That number comes from an evaluation protocol with two independent defects, reported in a measure that cannot size either one. The i…

🅲 hạng C
24
Fast and Strong Image Protection against Diffusion Personalization
📄 Paper arXiv cs.CR 13 giờ trước

arXiv:2611.22494v1 Announce Type: cross Abstract: Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from s…

🅲 hạng C
23
When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical Reasoning
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.14794v1 Announce Type: new Abstract: Proof-step verification rewrites a solver's answer into typed steps and uses LLM judges to certify or decline. We evaluate this pipeline on open-weight models across GPQA, AIME-2025, and a MATH-500 subset. Certification raises answ…

🅲 hạng C
23
Look It Up: Multi-bit LLM Watermarking via Codebook Search
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.16890v1 Announce Type: new Abstract: Attributing short LLM-generated texts to a specific source remains challenging for existing multi-bit watermarking methods, which often require long generations or costly decoding to recover payloads reliably. We propose a codebook…

🅲 hạng C
22
Security Authentication as Protective Friction: Understanding the Dual Effects of Authentication Measures in e-Government Platform
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19435v1 Announce Type: new Abstract: E-Government platforms, such as government credit platforms, handle highly sensitive personal data, requiring stringent security authentication (e.g., facial recognition, multi-factor verification) that protects users but impedes t…

🅲 hạng C
21
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 2 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
Model Annealing: Data-Efficient Learning through Review and Consolidation
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17524v1 Announce Type: new Abstract: A small labelled dataset is memorized long before the training budget runs out, and the one-hot labels that remain to be fitted then mostly sharpen confidence. Model annealing spends the rest of the budget on review and consolidati…

🅲 hạng C
21
Denoising the US Census: Succinct Block Hierarchical Regression
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2603.10099v2 Announce Type: replace-cross Abstract: The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed B…

🅲 hạng C
21
HubEgo-100K: In-the-Wild Egocentric Video of Skilled Work for Robot Learning
📄 Paper HF Daily Papers 2 ngày trước

Robot policies trained by imitation generalize poorly outside the environments and objects seen in training. Published data-scaling studies find that generalization grows with the diversity of training environments and objects rather than with more demonstrations per environment.…

🅲 hạng C
20
MEM-SQL: Memory-Empowered Text-to-SQL
📄 Paper HF Daily Papers 5 ngày trước

Text-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings where earlier queries over the same database can supply joins or calculations for …

🅲 hạng C
20
Factored One-sided Adam-Moment for Practical and Scalable SOAP
📄 Paper HF Daily Papers 6 ngày trước

Second-order optimizers (e.g., Shampoo, SOAP) have emerged as compelling alternatives to Adam/AdamW and promise faster per-step convergence than AdamW in transformer training. However, they still remain costly in practice, and even SOAP still pays substantial optimizer-state memo…

🅲 hạng C
20
The Value of Thinking: Learning When to Reason in Hybrid Decision Models
📄 Paper HF Daily Papers 6 ngày trước

Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. Rather than deciding how much to think, we explore a different paradigm, zero-or-T thinking: a single model…

🅲 hạng C