Search signals, briefings, company results, benchmarks and glossary terms.
Search signals, briefings, company results, benchmarks and glossary terms.
Use this view to inspect the underlying evidence corpus. For ranked developments, decision posture and interpretation, use Signals.
Raw feed or Signals?
Raw feed is chronological evidence. Signals ranks and interprets material change.
STRATA is a new research model for inferring race and ethnicity from names and geography, aiming to improve fair lending compliance under ECOA and HMDA.
Research explores Monte Carlo Dropout and entropy-thresholded selective prediction for robust brain tumor MRI triage, focusing on model confidence.
DiFA proposes a training-free framework for diffusion model inference that refines data prediction by accounting for statistical uncertainty.
Research introduces AEVAL, a deterministic testing framework for LLM agentic skill workflows to improve reproducibility and comparability.
Research introduces Jacobian-Aggregated Group Gradient (AGG) to reduce computational cost for Group Relative Policy Optimization (GRPO) in diffusion models.
FAME, a new Failure-Aware Mixture-of-Experts model, improves log anomaly detection by identifying specific anomalous messages, not just log groups.
A systematic review of Lipschitz continuity in deep learning explores its role in model robustness, generalization, and optimization dynamics.
Research explores hardware-aware design and optimization for edge intelligence systems, addressing complexity of deep learning on heterogeneous edge devices.
Research proposes a TabTransformer augmented by Boundary-Seeking GANs for robust intrusion detection, addressing class imbalance and adversarial attacks.
Research introduces a modular framework for verifying multi-agent system transitions and trajectories, operationalizing action language semantics.
Research identifies split conformal prediction maintains marginal coverage but fails silently on per-class coverage under distribution shift.
Research explores regret minimization for optimizing unknown, stochastic piecewise linear rewards in microeconomic models like contract design and auctions.
Research disentangles model (epistemic) and data (aleatoric) uncertainty in facial age estimation using Bayesian Neural Networks.
Research explores Thompson Sampling performance under model misspecification in dynamic decision-making, common in economic environments.
Research explores Differentiable Logic Gate Networks (Diff-Logic) for low-latency EEG classification on edge devices, compiling models into Boolean circuits.
A research paper proposes a Representation-Aware Distributionally Robust Optimization framework to improve model robustness against data shifts.
Research proposes a Novel Hybrid Quantum Reservoir Computing (nHQRC) framework to detect phase transitions in non-equilibrium dynamical systems.
Research introduces a three-level audit protocol to test for systematic asset-specific preferences and biases in financial large language models.
Researchers introduced ATLAS, a framework equipping Multimodal Large Language Models (MLLMs) with 'Think, Plan, Paint' reasoning for controlled image generation.
Research introduces ECO, an efficient learning framework for Neural Combinatorial Optimization using batched preference optimization and a Mamba backbone.
New research proposes a method for sparse-support uncertainty quantification, addressing issues of overconfident conclusions when dictionaries are learned from latent mixtures.
Research introduces SelectInfer, a method for selective neuron loading and computation to optimize LLMs for resource-constrained edge devices.
Deep Adaptive Bayesian Screening (DABS) introduces an offline policy network for adaptive factorial screening in high-dimensional discrete design spaces.
New research proposes Counterfactual Shapley Credit Assignment, a principled method to isolate policy skill from environmental stochasticity in RL agents.
Research explores LLM-based theorem proving by operating on abstract syntax trees to reduce token consumption and API costs for program verification.
A research paper proposes an 'AI epidemiology' framework to standardize expert-AI interaction data for prospective risk detection in deployed AI systems.
Sobek proposes a new method for streaming equivariant tensor product convolutions, reducing memory and improving GPU utilization for graph neural networks.
Research introduces a Stochastic Dimension Zeroth-Order Estimator to improve memory and training efficiency for Physics-Informed Neural Networks (PINNs).
CyberGym-E2E is a new large-scale, real-world benchmark for evaluating AI agents' end-to-end cybersecurity vulnerability discovery and remediation.
Research introduces RGMR, an inference-time framework adapting pre-trained foundation models for multi-scale temporal analysis and iterative refinement.
Research explores INT8 quantization, channel pruning, and spiking neural networks to improve efficiency of EEG seizure detection.
Research reveals gradient-free privacy leakage in federated language models (FLMs) through selective weight tampering, exposing sensitive client data.
Research proposes Precision-Varying Prediction (PVP) to robustify ASR systems against adversarial attacks by randomly sampling precision during inference.
Research finds low-rank optimizers like GaLore, used for memory-efficient LLM training, lack a stable, trackable subspace beyond a small core.
Research proposes OrderMoE, a method for deploying Mixture-of-Experts (MoE) models on edge devices by leveraging expert functional similarity.
New research introduces Rate-Distortion-Perception theory, extending classical rate-distortion to incorporate perceptual quality and semantic validity.
Research explores using LLMs to generate and optimize GPU kernel code for performance, focusing on validation and profiling for practical effectiveness.
Researchers propose Feature-Informed Diffusion Evolution (FIDE), a black-box framework for inverse rendering, bypassing differentiable renderers and gradient descent.
Research identifies security risks in integrating LLMs as AI components due to overlooked traditional software supply chain lessons.
Researchers propose Similarity-based Generative Network (SGN) for synthetic data generation robust to distribution shifts, reducing the need for target-domain optimization.
A research paper proposes a 'Brouwerian assertibility constraint' for responsible AI, requiring verifiable certificates for high-stakes assertions.
Research identifies a root cause for performance stagnation in PPO reinforcement learning, demonstrating that scaling to 1M parallel environments can prevent it.
Research identifies fundamental failures in marginal influence-based attribution methods for explaining global time series models due to computational mismatches.
Research introduces Time-Aware Prior Fitted Networks for zero-shot time series forecasting, leveraging exogenous variables to improve accuracy.
SEC-bench Pro is a new benchmark evaluating frontier LLMs' ability to find real software vulnerabilities and generate proof-of-concept exploits.
Research explores Role-Typed Credit Assignment (RTCA) for agentic reinforcement learning, improving credit distribution beyond standard GRPO for actions.
Researchers propose a multiverse-consensus pipeline for reproducible feature selection in untargeted LC-MS metabolomics, addressing pipeline decision variability.
Researchers introduced Retrieval-Augmented Interpretable Learning (RAIL), a meta-learning framework for zero-shot generation of interpretable models.
A research paper proposes a volatility-aware machine learning approach to detect extreme price movements in high-frequency financial markets.
Research explores lightweight wrappers for adapting Time Series Foundation Models (TSFMs) to regional forecasting, addressing proprietary weights and limited local data.
© 2026 OneBench: AI Insights. All rights reserved.
Evidence before opinion