Peter Szemraj PRO

pszemraj's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 13 days ago

From Word to World: Can Large Language Models be Implicit Text-based World Models?

Paper • 2512.18832 • Published 17 days ago • 11

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Paper • 2512.20757 • Published 15 days ago • 16

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published 15 days ago • 31

upvoted a paper 14 days ago

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

Paper • 2512.20352 • Published 15 days ago • 2

upvoted a paper 15 days ago

Are We on the Right Way to Assessing LLM-as-a-Judge?

Paper • 2512.16041 • Published 21 days ago • 32

upvoted a paper 16 days ago

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Paper • 2512.17909 • Published 19 days ago • 36

upvoted a collection 18 days ago

LLaDA 2.0

Collection

7 items • Updated 14 days ago • 39

upvoted a paper 19 days ago

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Paper • 2512.16649 • Published 20 days ago • 24

upvoted a collection 20 days ago

T5Gemma 2

Collection

3 items • Updated 20 days ago • 59

upvoted a paper 20 days ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published 23 days ago • 40

upvoted 3 papers 21 days ago

Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views

Paper • 2512.12980 • Published 24 days ago • 27

RePo: Language Models with Context Re-Positioning

Paper • 2512.14391 • Published 22 days ago • 8

Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation

Paper • 2512.13655 • Published 23 days ago • 2

upvoted a paper 22 days ago

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

Paper • 2512.12967 • Published 24 days ago • 103

upvoted 2 papers 23 days ago

Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in {pm 1, pm i}

Paper • 2512.02901 • Published Dec 2, 2025 • 5

Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems

Paper • 2512.11150 • Published 27 days ago • 5

upvoted a paper 24 days ago

Stronger Normalization-Free Transformers

Paper • 2512.10938 • Published 27 days ago • 19

upvoted a paper 25 days ago

BEAVER: An Efficient Deterministic LLM Verifier

Paper • 2512.05439 • Published Dec 5, 2025 • 35

upvoted 2 papers 29 days ago

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

Paper • 2512.07783 • Published about 1 month ago • 36

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

Paper • 2512.07525 • Published about 1 month ago • 57