samusenps

AI & ML interests

Foundational Architectures, Multi-Modality, Interpretability, Benchmarking w/ simulations, Robotics, Integration with Non envasive Open Source stack RISC-V BCI. Extremely high quality training data. Fully Open Source ML/AI.

Recent Activity

upvoted a paper 2 days ago

INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning

liked a Space 10 days ago

stepfun-ai/Step1X-Edit

liked a model 10 days ago

ByteDance/Dolphin

View all activity

Organizations

samusenps's activity

upvoted a paper 2 days ago

INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning

Paper • 2505.07291 • Published 26 days ago • 12

liked a Space 10 days ago

342

Step1X Edit

💻

Edit an image based on the given instruction.

liked a model 10 days ago

ByteDance/Dolphin

Image-Text-to-Text • Updated 11 days ago • 3.82k • 256

liked 2 models 14 days ago

Qwen/WorldPM-72B

Text Classification • Updated 21 days ago • 2.29k • 60

a-m-team/AM-Thinking-v1

Text Generation • Updated 24 days ago • 9.85k • • 180

liked a model 16 days ago

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • Updated 15 days ago • 9.94k • 979

upvoted 14 papers 16 days ago

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier

Paper • 2505.11966 • Published 21 days ago • 5

Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence

Paper • 2505.10176 • Published 23 days ago • 3

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

Paper • 2505.14633 • Published 17 days ago • 3

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

Paper • 2505.13731 • Published 18 days ago • 2

Learning to Highlight Audio by Watching Movies

Paper • 2505.12154 • Published 20 days ago • 3

Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation

Paper • 2505.11754 • Published 21 days ago • 2

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

Paper • 2505.11730 • Published 21 days ago • 5

KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models

Paper • 2505.14629 • Published 17 days ago • 1

Dynadiff: Single-stage Decoding of Images from Continuously Evolving fMRI

Paper • 2505.14556 • Published 17 days ago • 1

Phare: A Safety Probe for Large Language Models

Paper • 2505.11365 • Published 21 days ago • 7

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition

Paper • 2505.13380 • Published 18 days ago • 5

Visual Instruction Bottleneck Tuning

Paper • 2505.13946 • Published 18 days ago • 10

The Hallucination Tax of Reinforcement Finetuning

Paper • 2505.13988 • Published 18 days ago • 8

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits

Paper • 2505.14648 • Published 17 days ago • 8