cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5307, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Experience-Handoff Reinforcement Learning for Recursive Self-Improvement
📄 Paper HF Daily Papers 6 ngày trước

It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this …

🅲 hạng C
24
VoxMel TTS Technical Report
📄 Paper HF Daily Papers 3 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
24
Intent-Aware Protection for AI Agents
📄 Paper arXiv cs.CR 4 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
Veritas: A Verifier Generation Harness for Agent Tasks
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.13336v1 Announce Type: cross Abstract: The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges the outcome of each improvement round. However, the verifiers of most tasks are written by hand, which is expensive and does…

🅲 hạng C
23
Continuation-Guided LLM Evolution of Program Policies and Goal Compilers in Craftax
📄 Paper HF Daily Papers 4 ngày trước

Coding agents can synthesize and optimize code-based policies from simulator feedback, allowing the resulting program to act with zero inference model calls. But for long horizon tasks, two challenges arise: local improvements can hurt final success and switching to a new objecti…

🅲 hạng C
22
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 1 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
22
An Operationalization of Opaque Serial Depth
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverba…

🅲 hạng C
22
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…

🅲 hạng C
22
A Spectral Framework for Universal Proxy Regularization in Model Merging
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17728v1 Announce Type: new Abstract: Model merging constructs multi-task models without expensive joint training but often suffers from parameter interference. Some solutions mitigate this by constraining finetuning using data from the other tasks to be merged, violat…

🅲 hạng C
22
Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …

🅲 hạng C
22
DeCompCert: A Verified Decompiler for CompCert-Generated AArch64
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.18055v1 Announce Type: cross Abstract: DeCompCert is a Rocq-verified decompiler for AArch64 assembly generated by CompCert. It reconstructs CompCert C through nine reverse passes, combining deductively verified transformations with translation validation. Untrusted OC…

🅲 hạng C
21
LynnReal-Hand: Unlocking World Interaction with Hand Control
📄 Paper HF Daily Papers 2 ngày trước

Interactive video world models enable exploration through text and camera controls, yet direct object interaction requires finer control. Hands provide a natural interface, but translating continuous hand movements into coherent visual responses remains challenging because of com…

🅲 hạng C
21
GlyphAtlas: Disentangling Stroke Detail from Layout for Scene Text Synthesis
📄 Paper HF Daily Papers 3 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
21
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers
📄 Paper HF Daily Papers 5 ngày trước

As AI conference submissions grow rapidly, AI reviewers are being considered as an alternative. However, simply imitating human reviewing is problematic because reviewing serves multiple purposes, including evaluating papers' soundness, interestingness, and clarity, the last two …

🅲 hạng C
21
DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery
📄 Paper HF Daily Papers 5 ngày trước

Cities account for over two-thirds of the world's energy and more than 70% of global carbon dioxide emissions. City energy is essential for achieving the 2050 net-zero target and the UN's Sustainable Development Goals 7 and 11. Although existing studies have made progress, they a…

🅲 hạng C
20
SynthCorp: A Platform for Creating Benchmarks for Data Agents
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.14765v1 Announce Type: new Abstract: Current benchmarks for LLM-driven data agents saturate quickly and cannot target specific capabilities. We present SynthCorp, a platform that creates customizable data estates and benchmarks by simulating how business events produc…

🅲 hạng C
20
Rational Use of Time for Social Coordination in Humans and AI
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.14766v1 Announce Type: new Abstract: All social interactions are situated in time. Previous studies have shown that humans are able to use implicit temporal cues, such as the duration of a pause, to infer others' mental states. But how do humans use temporal cues for …

🅲 hạng C
20
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C
20
EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming
📄 Paper HF Daily Papers 6 ngày trước

Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce…

🅲 hạng C