Submitted by Minki Kang 35 ACON: Optimizing Context Compression for Long-horizon LLM Agents Microsoft 109 2
Submitted by Pranjal A. Chitale 7 The role of synthetic data in Multilingual, Multi-cultural AI systems: Lessons from Indic Languages Microsoft 2
Submitted by Ruiyu Wang 5 CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization Microsoft 3
Submitted by Xiao Liu 10 Behind RoPE: How Does Causal Mask Encode Positional Information? Microsoft 4 2
5 Accurate Chemistry Collection: Coupled cluster atomization energies for broad chemical space Microsoft
Submitted by Guangchen Lan 4 Contextual Integrity in LLMs via Reasoning and Reinforcement Learning Microsoft 13 1
2 TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance Microsoft
1 PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning Microsoft 7
Submitted by AK 262 Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Microsoft 42
Submitted by AK 34 WizardCoder: Empowering Code Large Language Models with Evol-Instruct Microsoft 9.48k 2