Samsung Research

company

https://research.samsung.com/

samsungresearch

AI & ML interests

None defined yet.

Recent Activity

AvinashAmballa submitted a paper 7 days ago

Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks

ABaldrati submitted a paper 2 months ago

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

xrxing submitted a paper 4 months ago

Trust Region On-Policy Distillation

View all activity

Papers

Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

View all Papers

submitted a paper to Daily Papers 7 days ago

Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks

Paper • 2609.22237 • Published Sep 3 • 8

submitted a paper to Daily Papers 2 months ago

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Paper • 2607.23373 • Published Jul 25 • 6

submitted a paper to Daily Papers 4 months ago

Trust Region On-Policy Distillation

Paper • 2606.01249 • Published May 31 • 47

submitted a paper to Daily Papers 5 months ago

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

Paper • 2605.13163 • Published May 13 • 7

submitted a paper to Daily Papers 6 months ago

RawGen: Learning Camera Raw Image Generation

Paper • 2604.00093 • Published Mar 31 • 21

submitted a paper to Daily Papers 7 months ago

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

Paper • 2603.10899 • Published Mar 11 • 7

submitted 2 papers to Daily Papers 8 months ago

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Paper • 2602.06694 • Published Feb 6 • 22

RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

Paper • 2602.05367 • Published Feb 5 • 8

submitted a paper to Daily Papers 8 months ago

MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling

Paper • 2602.03359 • Published Feb 3 • 10

submitted a paper to Daily Papers 8 months ago

Shallow-π: Knowledge Distillation for Flow-based VLAs

Paper • 2601.20262 • Published Jan 28 • 2

submitted a paper to Daily Papers 9 months ago

More Images, More Problems? A Controlled Analysis of VLM Failure Modes

Paper • 2601.07812 • Published Jan 12 • 6

in SamsungResearch/TRUEBench 10 months ago

[Update_25.12.24]

#4 opened 10 months ago by

updated a Space 10 months ago

TRUEBench

Explore and compare language model performance across categories and languages

submitted a paper to Daily Papers 10 months ago

PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs

Paper • 2512.14944 • Published Mar 13 • 36

submitted a paper to Daily Papers 10 months ago

VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs

Paper • 2512.12072 • Published Dec 12, 2025 • 18

in SamsungResearch/TRUEBench 10 months ago

[Update_25.11.26]

#3 opened 10 months ago by

updated a Space 12 months ago

TRUEBench

Explore and compare language model performance across categories and languages

in SamsungResearch/TRUEBench 12 months ago

[Update_25.10.15]

#2 opened 12 months ago by

updated a dataset 12 months ago

SamsungResearch/TRUEBench

Viewer • Updated Oct 15, 2025 • 142 • 123 • 32

in SamsungResearch/README 12 months ago

Update README.md

#2 opened 12 months ago by