All Articles
18316 articles total
PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement
PSCT-Net uses differentiable back-projection and attention-guided refinement to reconstruct 3D pediatric skull CTs from sparse X-rays.
FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming
FinRED is an expert-guided red-teaming framework specifically designed for evaluating the safety and regulatory compliance of financial LLMs.
SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models
SL-S4Wave is a self-supervised learning framework for physiological waveforms using structured state space models to capture long-range dependencies.
The Productivity J-Curve [pdf] (2018)
An exploration of the 'Productivity J-Curve', detailing the temporary dip in productivity that occurs when adopting new tools or processes.
Reinventing the Renaissance
A discussion on 'Reinventing the Renaissance', likely focusing on the intersection of art, technology, and intellectual revival.
Billionaire Ambani wants AI in every call, app, and home
Billionaire Ambani's Reliance is integrating AI into telecom services to reach over 500 million users across apps and homes.
The NTS Radio Player brings the best of internet radio to your hi-fi
NTS Radio and Atonemo have launched a dedicated high-fidelity radio player supporting 24-bit/192kHz audio and various streaming protocols.
Agentic Electronic Design Automation: A Handoff Perspective
A survey on agentic Electronic Design Automation (EDA) introducing the concept of 'handoff validity' and proposing a five-layer communication protocol (EACP).
Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation
Research on improving automatic speech recognition (ASR) for dysarthric speech using in-domain data augmentation with the Wav2Vec2 model.
Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
A vision for Policy-aware Vector Search to implement Fine-grained Access Control (FGAC) in vector databases for secure RAG pipelines.
ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number
Introduction of ParaScale, a plug-and-play module that uses a gauge-invariant 'Parallax Number' to transfer camera motion between videos of different scales.
Uncertainty-Aware Reward Modeling for Stable RLHF
Proposal of Uncertainty-Aware Reward Modeling (UARM) to reduce reward hacking in RLHF by using conformal prediction and variance decomposition in GRPO.
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis
Introduction of CREDENCE, a framework for decomposing compound sentences into atomic claims using a new Semantic-F1 metric for better fact-checking.
The film about Sam Altman has been dropped by Amazon MGM
Amazon MGM has reportedly dropped the upcoming film about OpenAI CEO Sam Altman, titled Artificial.
Our long national sunscreen nightmare is almost over
A Verge newsletter discusses the rise of TikTok trends suggesting people can build sun tolerance, which is medically inaccurate.
Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings
Research explores how sequential Direct Preference Optimization (DPO) affects previously learned preferences in LLMs.
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
The paper introduces Bayesian Manifold Curriculum (BMC) to improve LLM reasoning through structured, manifold-based task sampling.
Temporal Self-Imitation Learning
The Temporal Self-Imitation Learning (TSIL) framework improves robot manipulation efficiency by reusing successful trajectories.
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
SafeSpec is a framework that integrates risk estimation into speculative inference to make LLM decoding faster and safer.
Data Standards for Humanoid Robotics: The Missing Infrastructure for Physical AI
The paper argues for the development of international data standards to enable scalable and interoperable humanoid robot training.