会员服务
Boosting Visual Instruction Tuning with Self-Supervised Guidance
Arxiv
0+阅读 · 4月14日
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
Arxiv
0+阅读 · 4月27日
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Arxiv
0+阅读 · 3月13日
Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection
Arxiv
0+阅读 · 3月3日
Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
Arxiv
0+阅读 · 2月25日
ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
Arxiv
0+阅读 · 2月28日
PostTrainBench: Can LLM Agents Automate LLM Post-Training?
Arxiv
0+阅读 · 3月9日
QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery
Arxiv
0+阅读 · 2月19日
Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization
Arxiv
0+阅读 · 2月17日
An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation
Arxiv
0+阅读 · 2月16日
Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian
Arxiv
0+阅读 · 2月15日
Task-Conditioned Probing Reveals Brain-Alignment Patterns in Instruction-Tuned Multimodal LLMs
Arxiv
0+阅读 · 2月7日
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
Arxiv
0+阅读 · 2月2日
How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation
Arxiv
0+阅读 · 1月30日
Do Instruction-Tuned Models Always Perform Better Than Base Models? Evidence from Math and Domain-Shifted Benchmarks
Arxiv
0+阅读 · 1月19日
参考链接
微信扫码咨询专知VIP会员
Top