Our benchmark for multimodal unlearning methods
Alexey Dontsov
therem
b082f689-ebc3-413d-b1f2-27bd1e86dca7's profile picture
screemix's profile picture
chameleon-lizard's profile picture·
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration upvoted a paper 10 days ago
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures liked a model 23 days ago
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-DistilledOrganizations
models 30
therem/novel_ops_grpo_lora
Text Generation • Updated
therem/gemma_2_2b_matryoshka_sae
Updated
therem/llava-1.5-7b-CLEAR-forget-scrub
Updated
therem/llava-1.5-7b-CLEAR-forget-retain_ft
Updated
therem/llava-1.5-7b-CLEAR-forget-LLMU
Updated
therem/llava-1.5-7b-CLEAR-forget-KL
Updated
therem/llava-1.5-7b-CLEAR-forget-idk
Updated
therem/llava-1.5-7b-CLEAR-forget-grad_ascent
Updated
therem/llava-1.5-7b-CLEAR-forget-DPO
Updated
therem/llava-1.5-7b-CLEAR-finetune
Image-Text-to-Text • 7B • Updated • 42
datasets 24
therem/novel-ops-impossible
Viewer • Updated • 600 • 36
therem/novel-ops-reasoning
Viewer • Updated • 1.5k • 22
therem/all_math_generations
Viewer • Updated • 52.1k • 7
therem/deepseek_ai_deepseek_math_7b_instructHuggingFaceH4_MATH_500
Updated • 4
therem/qwen3_math_ai_minervamath_4x
Viewer • Updated • 1.09k • 9
therem/qwen3_math_ai_olympiadbench_4x
Viewer • Updated • 2.7k • 11
therem/qwen3_HuggingFaceH4_MATH_500_4x
Viewer • Updated • 2k • 9
therem/qwen_math_math_ai_minervamath_8x
Viewer • Updated • 2.18k • 7
therem/qwen_math_math_ai_olympiadbench_8x
Viewer • Updated • 5.39k • 6
therem/qwen_math_HuggingFaceH4_MATH_500_8x
Viewer • Updated • 4k • 4