Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
FastKernels: Benchmarking GPU Kernel Generation in Production
Foundation Protocol: A Coordination Layer for Agentic Society
Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation
Strategic Coercion Within Alliances: The Greenland Sovereignty Game as an AI Stress Test
Expressive Power of Deep Homomorphism Networks over Relational Databases
MUSEKG: A Knowledge Graph Over Museum Collections
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels
Weierstrass Positional Encoding for Vision Transformers
CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amp…
Leveraging Foundation Models for Causal Generative Modeling
Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommen…
Epistemic Skills: Reasoning about Knowledge and Oblivion
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
Robust Counterfactual Inference in Markov Decision Processes
FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Sys…
MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Liv…
A drone-based framework for coral habitat mapping via weakly supervised segmentation
KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Usin…