Nicky's picture

Nicky

NickyNicky

·

AI & ML interests

None yet

Recent Activity

liked a model about 2 hours ago

SakanaAI/TinySwallow-1.5B-Instruct

liked a model about 2 hours ago

Vision-CAIR/LongVU_Llama3_2_1B

reacted to singhsidhukuldeep's post with 🔥 about 7 hours ago

Exciting Research Alert: Revolutionizing Complex Information Retrieval! A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges. >> Key Innovations Information Alignment The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs. Structure Alignment ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching. Self-Verification The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness. >> Performance Highlights The results are impressive: - Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset - Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA - Reduces the number of required LLM calls while maintaining superior retrieval quality >> Technical Implementation The system uses a three-step process: 1. N-gram indexing and embedding computation for all data objects 2. Constrained beam decoding for information alignment 3. Mixed-integer programming optimization for structure exploration This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.

View all activity

Organizations

NickyNicky's activity

New activity in open-thoughts/OpenThinker-7B 6 days ago

Thank you very much for this model, I have questions

#1 opened 6 days ago by

New activity in m-a-p/YuE-s1-7B-anneal-en-cot 6 days ago

wow model, thank

#6 opened 6 days ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 7 days ago

how to fine tune?

#10 opened 7 days ago by

New activity in weqweasdas/RM-Gemma-2B 11 days ago

model RM how?

#2 opened 11 days ago by

New activity in NickyNicky/Human-Like-DPO-Dataset_deduplicated_and_duplicated 13 days ago

Librarian Bot: Add language metadata for dataset

#2 opened 17 days ago by

New activity in jinaai/ReaderLM-v2 18 days ago

What advantage does this have over normal algorithmic ways of turning HTML to Markdown ?

#5 opened 18 days ago by

New activity in cognitivecomputations/Dolphin3.0-Llama3.2-3B 28 days ago

great gift from the wise men

#1 opened 28 days ago by

New activity in PowerInfer/SmallThinker-3B-Preview about 1 month ago

example use colab?

#3 opened about 1 month ago by

New activity in hexgrad/Kokoro-82M about 1 month ago

ONNX usage

#14 opened about 1 month ago by

New activity in fishaudio/fish-speech-1.5 2 months ago

notebook Colab

#3 opened 2 months ago by

New activity in OuteAI/OuteTTS-0.1-350M-GGUF 3 months ago

error load model

#3 opened 3 months ago by

New activity in OuteAI/OuteTTS-0.1-350M 3 months ago

Error: Exception: data did not match any variant of untagged enum ModelWrapper at line 352271 column 3

#1 opened 3 months ago by

New activity in KingNish/Reasoning-Llama-3b-v0.1 3 months ago

dataset generated by this model

#3 opened 3 months ago by

New activity in arcee-ai/Arcee-Agent 7 months ago

Thank you very much for this model, I have questions.

#1 opened 7 months ago by

New activity in instruction-pretrain/InstructLM-1.3B 8 months ago

Thanks for the models and data, I have some questions.

#2 opened 8 months ago by

New activity in davanstrien/similarity-dataset-sc2-8b 8 months ago

hola, gracias por el dataset.

#1 opened 8 months ago by

New activity in arcee-ai/Llama-3-SEC-Chat 8 months ago

Great model !!!

#1 opened 8 months ago by

New activity in cognitivecomputations/dolphin-2.9.3-qwen2-1.5b 8 months ago

model multi-turn?

#1 opened 8 months ago by

New activity in Qwen/Qwen2-1.5B-Instruct 8 months ago

model multi-turn?

#2 opened 8 months ago by

New activity in stabilityai/stable-audio-open-1.0 8 months ago

Any Comfy workflow ?

#1 opened 8 months ago by