Samsung Research

Samsung Research on Hugging Face Daily Papers: 13 papers, 0 in the top 3 of their day, 0 paper of the day.

  1. Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks 7 upvotes, #26 of 2026-09-28
  2. UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models 6 upvotes, #22 of 2026-07-28
  3. Trust Region On-Policy Distillation 43 upvotes, #4 of 2026-06-03
  4. LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters 9 upvotes, #30 of 2026-05-22
  5. RawGen: Learning Camera Raw Image Generation 20 upvotes, #15 of 2026-04-01
  6. LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation 6 upvotes, #18 of 2026-03-16
  7. NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models 15 upvotes, #23 of 2026-02-10
  8. RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs 7 upvotes, #24 of 2026-02-09
  9. MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling 9 upvotes, #30 of 2026-02-05
  10. Shallow-π: Knowledge Distillation for Flow-based VLAs 2 upvotes, #20 of 2026-01-29
  11. More Images, More Problems? A Controlled Analysis of VLM Failure Modes 6 upvotes, #19 of 2026-01-19
  12. Puzzle Curriculum GRPO for Vision-Centric Reasoning 33 upvotes, #7 of 2025-12-18
  13. VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs 17 upvotes, #10 of 2025-12-18

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.