🧠 AI Research - obaqueiro · Scour

Embedding Hybrid Systems into Continuous Latent Vector Fields

⚙️ML Engineering Academic

Minibatch Selection via Partition Matroid Constrained Gradient Matching

💬LLMs Academic

Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

💬LLMs Academic

Flexible Kernels for Protein Property Prediction

💬LLMs Academic

Variational Proximal Policy Optimization

🤖AI Academic

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network

⚙️ML Engineering Academic

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

⚙️ML Engineering Academic

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

💬LLMs Academic

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

⚙️ML Engineering Academic

Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models

💬LLMs Academic

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

⚙️ML Engineering Academic

UniSVQ: 2-bit Unified Scalar-Vector Quantization

💬LLMs Academic

Preserving Plasticity in Continual Learning via Dynamical Isometry

💬LLMs Academic

Compositional Generative Modeling from Decentralized Data

💬LLMs Academic

LLM Self-Recognition: Steering and Retrieving Activation Signatures

💬LLMs Academic

UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning

🤖AI Academic

Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity

💬LLMs Academic

Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning

🏗️System Design Academic

Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models

⚙️ML Engineering Academic

Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

🛡️AI Safety Academic

Sign up or log in to see more results

Log in to enable infinite scrolling