The Archive

STAG network jointly models motion flow and facial connectivity for micro-expression recognition via spatio-temporal action units.

OPI framework uses ontology-guided relation constraints to reduce noise in multi-hop knowledge graph question answering.

JD Oxygen AIIC: industrial-scale LLM/VLM system for SKU understanding and management across billions of e-commerce items.

OperatorSHAP efficiently computes Shapley values for neural operators on irregular grids for safety-critical physical applications.

LLMs applied to data fusion/truth discovery in tabular data via prompting strategies for single and multi-truth scenarios.

ToolPrivacyBench evaluates purpose-bound privacy in multi-tool LLM agent trajectories, filling gap in agent evaluation.

MultiHashFormer enables parameter-efficient hash-based autoregressive language models using multi-hash signatures.

Study shows LLM self-evaluation is not uniformly easier than generation; multi-hop QA reveals attention-based mechanistic differences.

Voice-based speaker clustering framework for insurance fraud detection in call-centre environments using speaker linking.

Extractive-abstractive hybrid summarization for legal case judgements using tree-of-thoughts with DeepSeek and Llama.

Systematic study of domain gap in diffusion-based satellite image super-resolution across Sentinel-2 and PlanetScope.

MLVC: cross-platform neural video codec with deterministic hardware-robust entropy coding for practical deployment.

Lifted Causal Inference applies relational lifted inference to causal graphical models via parametric causal factor graphs.

Signal-coverage matrix stratifies LLM autoformalization errors (type vs. semantic) across ProofNet# and MiniF2F using DeepSeek V4-Pro.

OpenAI previews GPT-5.6 Sol with enhanced coding, science, and cybersecurity capabilities and advanced safety measures.

Analysis of geopolitical security implications of US Fable/Mythos suspension limiting domestic cybersecurity patching capability.

OpenAI internal Codex usage surged 13–56x across departments since Nov 2025, with Research leading adoption.

Cohere publishes practical guide on building AI agents for enterprise automation, covering reliability, security, and deployment patterns.

penAI reportedly plans to share its newest model, GPT 5.6, with a select group of partners instead of to the broader public. The reason: the Trump administration told it to.

Bruce Schneier argues companies deploying AI should face legal liability for errors, citing German ruling against Google's AI summaries.

Shaders are GPU programs that process visual data—such as rays, pixels, geometry, and textures—to produce specific rendering effects. Shaders find necessary... Shaders are GPU programs that process visual data—such as rays, pixels, geometry, and textures—to produce specific rendering effects. Shaders find necessary data through a process called resource binding. CPU code orchestrates the creation of GPU resources such as textures and memory buffers and then carefully arranges for shader code to access them through a binding protocol. Source

The Trump administration, apprehensive of potential security issues, has reportedly asked OpenAI to stagger the release of its next big-ticket model, GPT-5.6. The Information reported that OpenAI CEO Sam Altman told employees Wednesday in a company Q&A that it would release GPT-5.6 in limited preview form - granting access only to a small group of enterprise customers - in compliance with a request from the federal government. During that preview period, the Trump administration itself would reportedly approve access for customers on a case-by-case basis. It's a more favorable deal than the T...

Agent testing startup Patronus AI, founded by former Meta AI researchers, is experienced nearly insatiable demand, its investor says.

User-built meta-tracker aggregating 17+ status checkers for Fable 5 access restoration.

Notion is "going all in on using agents to run your inbox."

It took 20 years, but the Finance app arrives just in time to be packed full of AI.

Alibaba allegedly used 25,000 accounts to mine Claude over 28.8 million exchanges.

DanceOPD uses on-policy distillation to unify text-to-image, local and global editing in flow-matching models by resolving capability conflicts.

RiVER framework enables RL training of LLMs on optimization tasks without ground-truth answers using continuous execution feedback.