Planet AI Developer Filter
SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs
Abstract page for arXiv paper 2608.25068: SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs
Community feed
doyaken.ai
A focused stream of recent stories from the sources curated for this community. Latest: SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs, Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping, and A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards. Page 50.
Search
Planet AI Developer Filter
Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping
Abstract page for arXiv paper 2608.24956: Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping
Planet AI Developer Filter
A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards
Abstract page for arXiv paper 2608.24935: A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards
Planet AI Developer Filter
Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation
Abstract page for arXiv paper 2608.24934: Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation
Planet AI Developer Filter
DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
Abstract page for arXiv paper 2608.25061: DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
Planet AI Developer Filter
Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection
Abstract page for arXiv paper 2608.25028: Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection
Planet AI Developer Filter
The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure
Abstract page for arXiv paper 2608.25005: The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure
Planet AI Developer Filter
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Abstract page for arXiv paper 2608.24988: Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Planet AI Developer Filter
Unsupervised Post-Training of Foundation Models: A Survey
Abstract page for arXiv paper 2608.24982: Unsupervised Post-Training of Foundation Models: A Survey
Planet AI Developer Filter
Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment
Abstract page for arXiv paper 2608.24920: Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment
Planet AI Developer Filter
Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores
Abstract page for arXiv paper 2608.24901: Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores
Planet AI Developer Filter
Demystifying Reinforcement Learning Post-Training of Language Models
Abstract page for arXiv paper 2608.24949: Demystifying Reinforcement Learning Post-Training of Language Models
More stories
More stories load automatically as you scroll.