Kevin Roose Didn’t Use AI to Write His Book About AI

The author of The AGI Chronicles says his book “was written by a very tired, overworked, under-slept human being.”

Game Decompilation, Is This Legal?, A Well-Trodden Path

Games are being decompiled, but the real risk to gaming is new games and increased personalization.

Game Decompilation, Is This Legal?, A Well-Trodden Path

Games are being decompiled, but the real risk to gaming is new games and increased personalization.

基于 Vaultwarden 和 Keyguard 的自托管密码管理实践

密码管理服务的数据，当然要掌握在自己手里。<a href="https://sspai.com/post/115416" target="_blank">查看全文</a>

基于 Vaultwarden 和 Keyguard 的自托管密码管理实践

密码管理服务的数据，当然要掌握在自己手里。<a href="https://sspai.com/post/115416" target="_blank">查看全文</a>

Advancing computer use with Ironclad

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

Ofcom investigates Meta over Instagram Instants feature

The regulator said Instagram had not fully assessed risks posed by its Instants feature prior to launching it.

不er，咋陶哲轩也成AI减速派了？？

stable

n8n@2.42.3

n8n@2.42.3

n8n@2.43.0

n8n@2.43.0

beta

Lego fraudster among last year's most high-profile insurance scammers

The person was sentenced to 28 months in prison after an investigation found the claims were made up, the insurance trade body, the ABI said.

OpenAI「疯狂28天」首日，这都发了些啥啊…

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

火箭发动机的“技术鄙视链”

猛禽之后，中国火箭也在追全流量补燃。

火箭发动机的“技术鄙视链”

猛禽之后，中国火箭也在追全流量补燃。

世界模型赛道：谁在收编，谁在突围？

芯片巨头们开抢模型

重塑苹果设计团队核心地位，特努斯瞄准下一个十年竞争

而当设计团队地位被再次拔高，乃至可能成为苹果产品开发起点，那么苹果在AI时代能否复刻iPhone神迹，用全新产品范式开启下一个十年，我们拭目以待。

AI 越来越强，公司为什么还是做不快？

成果看起来越完整，剩下的工作越容易被误解为拖延。

The Reported Engagement with AI Level (REAL) Rating: A Framework for Disclosing Human-AI Collaboration

arXiv:2610.04021v1 Announce Type: new Abstract: Generative artificial intelligence has become increasingly incorporated into digital media and more generally into production workflows with which the public frequently interacts. Current provenance standards and disclosure methods frequently rely on binary categorizations, differentiating only between entirely human-authored and AI-generated content

Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale

arXiv:2610.04002v1 Announce Type: new Abstract: A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whether this token-specific parameterization is required for substantial language-modeling capability, or whether a shared Transformer can learn from fixed token identities. We compare three decoder-only language models trained from scrat

Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction

arXiv:2610.04056v1 Announce Type: new Abstract: Synthesizing realistic graphs at scale is vital when the graphs of interest are large and real-world samples are limited or access-sensitive. Diffusion-based generators have recently driven much of the progress, offering high modeling capacity, but most such methods have quadratic computational complexity and are hence restricted to small-scale netwo

REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers

arXiv:2610.03888v1 Announce Type: new Abstract: Reconstructing global sea surface pH from sparse observations is critical for monitoring ocean acidification and understanding marine carbon cycling. Traditional assimilation and inverse models are physically grounded but costly for large-scale reconstruction. Recent black-box and physics-guided AI models improve efficiency, but are mainly designed f

Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents

arXiv:2610.04040v1 Announce Type: new Abstract: Financial LLM agents are often evaluated by comparing their end-to-end returns with those of a baseline and testing the paired difference against zero. This measures whether deploying the agent changes realized performance, but it does not isolate event-selection skill. An agent that frequently changes positions from flat to long can earn a positive

The Independence Prior of SAEs Fragments Visual Concepts

arXiv:2610.04112v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) decompose model activations into sparse combinations of interpretable dictionary atoms. Although SAEs are grounded in the Linear Representation Hypothesis (LRH), their objective smuggles in an additional prior: concepts across patches are treated as independent, an assumption clearly violated by natural images and by the ac

CUAWright: A Minimal Unified Interface for Digital Agents

arXiv:2610.04116v1 Announce Type: new Abstract: The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that are fixed before task execution. As models' coding capabilities improve, the GUI native and static harness prevents them from direct programmatic operation on system state, as well a

Agentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation

arXiv:2610.04188v1 Announce Type: new Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In this paper, we have studied the spatial capabilities of advanced generative AI to understand the rotations of objects in 3D space, utilizing AI's image processing and language processing features. We train

Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents

arXiv:2610.04168v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are commonly implemented as an LLM in a loop with Planning, Memory, Tools, and Control Flow. This application-focused view connects agentic LLM research with deployable systems and leaves open how such systems should be evaluated beyond end-to-end task success. Building on this view, we define agentic cognit

SHarP: Saliency-based Pruning of Agent Harnesses

arXiv:2610.04178v1 Announce Type: new Abstract: Agent harnesses are systems that coordinate model calls, tool use, and task execution to help large language models complete complex tasks. To meet task requirements and address failures, these systems are often iteratively refined by amending and patching their instructions, tools, and workflows, continuously increasing harness complexity. It is the

Language Model Activations Inhabit Privileged Error-Correcting Basins

arXiv:2610.04183v1 Announce Type: new Abstract: Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize that this robustness is a result of passive dynamics, i.e., constraining mechanisms in the forward pass that funnel activations toward "good" regions that produce coherent o

EvalResearchBench: Can AI Agents Design Their Own Evaluations?

arXiv:2610.04184v1 Announce Type: new Abstract: Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this design process and introduce EvalRe

Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation

arXiv:2610.04006v1 Announce Type: new Abstract: Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body proportions. We introduce a verifier-guided augmentation framework that uses global and mode-local PCA to generate inexpensive candidates, screens them using corr

InvestigationWorlds: An Agentic Environment for Legal Investigation

arXiv:2610.04129v1 Announce Type: new Abstract: We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summary judgment motion. This motion relies upon a record composed of real evidence exhibits, and results in a court-adopted hypothesis that is treated as ground truth for the purposes of deciding the motio

VolS-GS: Relightable Gaussian Splatting with Volumetric Subsurface Scattering

arXiv:2610.04007v1 Announce Type: new Abstract: We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints. Relightable Gaussian Splatting methods typically model appearance independently at each primitive, which makes non-local effects difficult to represent. This limitation

Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning

arXiv:2610.04003v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, under strict constraints on compute and memory. Existing approaches lie along a difficult trade-off: simple fine-tuning is computationally efficient but suffers from catastrophic forgetting, replay-based

Streaming Multi-Track Timeline Control for 3D Human Motion Generation

arXiv:2610.03873v1 Announce Type: new Abstract: Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applications require responding to new instructions while continuing ongoing actions, such as answering a phone while walking. Existing approaches address streaming generation or simultaneous composition wit

Learning Subject-Specific Anatomical Representations via Manifold Expansion: Application to Accelerated Multi-Contrast MRI

arXiv:2610.04028v1 Announce Type: new Abstract: Clinical MRI routinely acquires multiple contrast-weighted images of the same anatomy for complementary tissue characterization. However, current accelerated MRI methods typically reconstruct each contrast independently, without fully exploiting shared anatomical information. This work aims to learn anatomical representations invariant to contrast-de

LoRA Direction Extraction for Controllable Light Toggling in FLUX.1 Kontext

arXiv:2610.03771v1 Announce Type: new Abstract: We propose a fine-tuning method for flow-matching diffusion models aimed at realistic artificial light modeling without the need for a large training dataset. We address the task of controllable interior image editing, where the goal is to turn artificial light sources on or off while preserving the scene geometry, object placement, materials, and vi

Energy Variation in Training Modern Computer Vision Architectures

arXiv:2610.03772v1 Announce Type: new Abstract: The rapid growth of deep learning has substantially increased the energy consumption associated with model training, making energy efficiency an increasingly relevant design criterion. This study empirically measures the energy variation of training seven modern computer vision architectures, MobileNetV3-Small, MobileNetV3-Large, EfficientNet-B0, Eff

Least Squares for Time Series Forecasting

arXiv:2610.03812v1 Announce Type: new Abstract: A time-series forecast is scored on a future value of the series. A representation loss that regresses the next latent, as in LeNEPA, is a different least-squares problem on the same bottleneck. We write both programs down. The forecast program minimizes the error of a decoded latent on the coordinate that will be reported. For a scalar target and a

ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity

arXiv:2610.04020v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingly used not only for passive analysis but also for active interventions such as unlearning, bias mitigation, and concept editing. A central challenge for these editing and steering methods is reliably

MAGEFormer: Learning Metric-Consistent Representations for Anisotropic CT Segmentation

arXiv:2610.04036v1 Announce Type: new Abstract: Vision Transformers (ViTs) have shown strong performance in volumetric segmentation, but their effectiveness on clinical CT is limited by an isotropic Euclidean lattice assumption. This conflicts with anisotropic CT acquisition, leading to two key issues: (1) a metric mismatch between voxel indices and physical anatomy, and (2) accuracy degradation f

LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction

arXiv:2610.03834v1 Announce Type: new Abstract: Short-term bike-sharing demand forecasting is complicated by spatial-temporal non-stationarity and the practical difficulty of incorporating unstructured external text into numerical pipelines. Conventional approaches rely on historical flow sequences and fixed graph structures, thereby constraining their accuracy when anomalous social events perturb

Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents

arXiv:2610.04409v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools or generating invalid calls. Existing mitigation methods report substantial improvements, yet we identify a previously overlooked failure mode that we term Hallucination Esc