arxiv:2610.08902
Harman Singh PRO
harman
AI & ML interests
NLP, Multimodal
Recent Activity
authored a paper 3 days ago
Agent Plasticity: Measuring Self-Improvement Through Experience authored a paper 3 days ago
Gemma 3 Technical Report authored a paper 3 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL RolloutsOrganizations
models 39
harman/gemma2-9b_skyworks20k_RM_BT
Feature Extraction • 9B • Updated • 10
harman/gemma2-9b_ultrainteract60k-RM_BT
Text Classification • 9B • Updated • 10
harman/gemma2-9b_ultrafeedback-CARMA-qrandomized_neutrals_our_improve_degrade_data_BT
Text Classification • 9B • Updated • 7
harman/gemma2-9b_ultrafeedback-rrm_BT
Text Classification • 9B • Updated • 13
harman/gemma2-9b_ultrafeedback-RM
Text Classification • 9B • Updated • 9
harman/gemma2-9b_ultrafeedback-CARMA_originalplusoursall_AND_rrm_sampled_aug_plus_original_wo_neutrals
Feature Extraction • 9B • Updated • 11
harman/qwen2p5-7b_ultrafeedback-RRM_pairpm_v2
Feature Extraction • 7B • Updated • 16
harman/qwen2p5-7b_ultrafeedback-CARMA_qrandomized_neutrals_our_improve_degrade_data_all_BT
Feature Extraction • 7B • Updated • 13
harman/qwen2p5-7b_ultrafeedback-CARMA_qrandomized_neutrals_our_improve_degrade_data_all_pairpm
Feature Extraction • 7B • Updated • 16
harman/qwen2p5-7b_ultrafeedback-RRM_BT
Feature Extraction • 7B • Updated • 14
datasets 129
harman/tts-datagen
Viewer • Updated • 468k • 256
harman/tts
Updated • 123
harman/v1-verification-datasets
Viewer • Updated • 575 • 22
harman/deepcoder_solver_genagg_qwen4b_instruct_deepcoder_50p
Viewer • Updated • 24.3k • 11
harman/deepcoder_solver_genagg_qwen4b_instruct_50p
Viewer • Updated • 24.3k • 41
harman/deepcoder-train-qwen4b-instr-tok-mean_bs64_roll4-run3_step50-codeonly_truncation_inferenceprompt
Viewer • Updated • 24.3k • 22
harman/deepcoder-train-Qwen_qwen3-4b-instruct-2507-codeonly_truncation_inferenceprompt
Viewer • Updated • 24.3k • 22
harman/deepcoder-test-Qwen_qwen3-4b-instruct-2507-codeonly_truncation
Viewer • Updated • 10 • 25
harman/deepcoder-test-deepcoder-qwen4b-instruct-cont-temp0_6-32k-hsrun_step230-codeonly_truncation
Viewer • Updated • 687 • 71
harman/deepcoder-train-deepcoder-qwen4b-instruct-cont-temp0_6-32k-hsrun_step230-codeonly_truncation
Viewer • Updated • 24.3k • 274