https://github.com/ConfluxConflux/mechaptcha
Siddharth M. Bhatia
siddharthmb
·
AI & ML interests
None yet
Recent Activity
updated a model about 7 hours ago
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B published a model about 7 hours ago
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B updated a model about 7 hours ago
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Qwen3-8BOrganizations
https://github.com/Sid-MB/transcoder-adapters
-
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs4_sl14700393
4B • Updated • 6 • 1 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr3e-04_bs4_sl14701500
4B • Updated • 3 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs2_sl14700755
4B • Updated • 3 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs1_sl14700794
4B • Updated • 4
https://github.com/ConfluxConflux/mechaptcha
https://github.com/Sid-MB/transcoder-adapters
-
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs4_sl14700393
4B • Updated • 6 • 1 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr3e-04_bs4_sl14701500
4B • Updated • 3 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs2_sl14700755
4B • Updated • 3 -
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs1_sl14700794
4B • Updated • 4
models 108
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B
Updated
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Qwen3-8B
Updated
siddharthmb/2026.RA.Fairness-GRPO-lam1
Reinforcement Learning • Updated
siddharthmb/2026.RA.Fairness-GRPO-lam0
Reinforcement Learning • Updated
siddharthmb/mats-gf-metadata-tags-adapters
Updated
siddharthmb/mats-gf-metadata-tags-probes
Updated
siddharthmb/mats-gf-provenance-demo-qwen3-8b
Text Generation • 8B • Updated • 33
siddharthmb/mats-gf-provenance-codewords-adapters
Updated
siddharthmb/mats-gf-latent-tool-memory-triggers
Feature Extraction • Updated
siddharthmb/mats-gf-olmo3-7b-planted-beliefs
Text Generation • 7B • Updated • 32
datasets 51
siddharthmb/2026.RA.SelfHarm-Polarity-Arm
Preview • Updated
siddharthmb/2026.RA.QKV-Attention-Interface
Viewer • Updated • 7.36k • 92 • 1
siddharthmb/2026.RA.Fairness-Counterfactual-Pairs
Viewer • Updated • 52.1k • 38
siddharthmb/2026.RA.Five-Seat-Framing-Qwen-Robustness
Updated • 76
siddharthmb/2026.RA.Five-Seat-Qwen3-8B-Robustness
Viewer • Updated • 1 • 37
siddharthmb/2026.RA.Public-Oracle-Gap
Updated • 1.18k
siddharthmb/2026.RA.Five-Seat-Frontier-Negotiation
Viewer • Updated • 1.22k • 309
siddharthmb/2026.RA.Frontier-and-Scale-Cells
Viewer • Updated • 28k • 186
siddharthmb/2026.RA.Fairness-GRPO
Preview • Updated • 59
siddharthmb/2026.RA.NBS-Channel-Comparison
Viewer • Updated • 972 • 59