Channels - Many-Shot CoT-ICL: Making In-Context Learning Truly Learn :: FRELIP Discovery

Similar Items: Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Quick Look
SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
Quick Look
Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
Quick Look
The Impossibility Triangle of Long-Context Modeling
Quick Look
Long Context Pre-Training with Lighthouse Attention
Quick Look
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
Quick Look
A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches for Sentiment Classification on IMDb Movie Reviews
Quick Look
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
Quick Look
Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
Quick Look
Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts
Quick Look
SkillOS: Learning Skill Curation for Self-Evolving Agents
Quick Look
When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
Quick Look
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
Quick Look
RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning
Quick Look
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
Quick Look
Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
Quick Look
Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
Quick Look
Segmenting Human-LLM Co-authored Text via Change Point Detection
Quick Look
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
Quick Look
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
Quick Look
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
Quick Look
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
Quick Look
Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish
Quick Look
A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
Quick Look
A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language