Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Incl…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
AI-Driven Alpha Decay: Algorithmic Homogenization, Reflexive Signal Erosion, and the Para…
VineLM: Trie-Based Fine-Grained Control for Agentic Workflows
KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing
EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed …
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Nano World Models: A Minimalist Implementation of Future Video Prediction
Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcemen…
Harnessing AtomisticSkills for Agentic Atomistic Research
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode M…
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Appro…
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon…
Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning
StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs
Mixture of Complementary Agents for Robust LLM Ensemble
World-State Transformations for Neuro-symbolic Interactive Storytelling
Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions
Feature Lottery? A Bifurcation Theory of Concept Emergence
Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixe…
ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Ag…
Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discre…
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Hist…
Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning
Grammatically-Guided Sparse Attention for Efficient and Interpretable Transformers
When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Inte…