Papers

Quick overviews of the latest science and technology preprint and open access research publications. Short and to the point for busy professionals.

Science & Technology
PAPERS

Deep Overviews of Cutting Edge Research

Advertise Here!

Gain premium exposure to our growing audience of professionals. Learn More

Inquire Now

SWE-Bench Pro Sets A Higher Bar For AI Coding Agents

As AI coding agents approach human-level performance on existing benchmarks, the research community faces a critical challenge: how do we continue measuring progress when current evaluation suites are...

AI benchmarks coding agents software engineering

Sep 23, 2025

0 2596

SciVer Puts Multimodal Claim Verification To The Test

Scientific claim verification and reproducibility have emerged as a critical challenges in the era of information abundance and multimodal AI systems. Unlike traditional fact-checking that relies prim...

AI benchmark claim verification multimodal scientific reasoning

Sep 23, 2025

0 627

Sustainable Electrochemical-Magnetic Biosensor From Recycled Materials

Creating effective diagnostic tools from waste materials might sound like science fiction, but researchers have developed a COVID-19 biosensor built from recycled battery graphite and plastic cups. Th...

biosensor circular economy COVID-19 electrochemistry magnetic nanoparticles

Sep 23, 2025

0 528

Defeating Nondeterminism In LLM Inference

Reproducible outputs at temperature 0 should be straightforward in principle, the sampler always picks the highest probability token, yet production LLM endpoints still produce different completions f...

attention batch-invariance determinism gpu-kernels llm-inference

Sep 23, 2025

0 1892

Uni-LoRA: Ultra-Efficient Parameter Reduction For LLM Training

Low-Rank Adaptation (LoRA) revolutionized how we fine-tune large language models by introducing parameter-efficient training methods that constrain weight updates to low-rank matrix decompositions (Hu...

computational efficiency isometric projections linear algebra LoRA machine learning mathematics neural networks optimization parameter efficiency projection methods

Sep 20, 2025

0 561

Scaling Laws Unveiled: The Mathematical Blueprint Behind Smarter, Cheaper AI Models

Training a state-of-the-art language model can cost tens of millions of dollars and months of computation time, not to mention the expertise needed for development. Yet until now, researchers have bee...

AI Chinchilla deep learning GPT-3 language models machine learning neural networks optimization principal component analysis scaling laws statistical methodology

Sep 20, 2025

0 737

EpMAN Reweights Attention With Episodic Memory To Tackle 256k-Token Contexts

Long-context reasoning is still a weak spot for many large language models, even as context windows grow. The ACL 2025 paper EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts ...

ACL 2025 attention episodic-memory LLM long-context RAG

Sep 17, 2025

0 1177

UItron Sets a Higher Bar for GUI Agents

UItron is an open-source foundation model for GUI agents that tackles a hard problem in computer use automation: understanding complex interfaces and turning natural language goals into precise on-scr...

GUI agents OSWorld Reinforcement learning ScreenSpot VisualWebBench

Sep 17, 2025

0 3124

Dimension-Insensitive Metrics: DIEM vs. Cosine Similarity In High Dimensions

The paper " Surpassing Cosine Similarity for Multidimensional Comparisons: Dimension Insensitive Euclidean Metric " interrogates a default choice in machine learning and information retrieval: cos...

cosine similarity distance metrics embeddings euclidean distance NLP similarity

Sep 13, 2025

0 1859

Building a Molecule to Fight Tuberculosis: The Total Synthesis of Brevianamide S

The brevianamide alkaloids represent a structurally fascinating subset of fungal diketopiperazine dimers, with most family members featuring characteristic tryptophan-tryptophan oxidative linkages. Br...

aldol condensation antitubercular brevianamide S diketopiperazine organic chemistry Stille coupling total synthesis

Sep 12, 2025

0 1199

AI Agent Achieves Gold Medal Performance on IPhO 2025 Physics Competition

In a remarkable demonstration of artificial intelligence's advancing capabilities, researchers from Princeton University and collaborating institutions have developed Physics Supernova, an AI agent sy...

Sep 11, 2025

0 2640

mmBERT: How Johns Hopkins Built a 1,833-Language AI That Outperforms XLM-R

mmBERT: How Johns Hopkins Built a 1,833-Language AI That Outperforms XLM-R Imagine trying to build an AI system that truly understands human language not just in English, but in over 7,000 languages s...

AI research annealed language learning cross-lingual digital inclusion encoder-only FlashAttention Gemma tokenizer GLUE inverse masking language model mmBERT ModernBERT MTEB multilingual NLP XLM-R XTREME

Sep 10, 2025

0 4180

Get All The Latest Research & News!

Subscribe

Our latest content

Check out what's new !

See all

Get In Front of 1000s of Professionals Today! Advertise Here

Most Popular Articles

Check out what the hot topics are!

See all

Follow us

Science & Technology
PAPERS

Advertise Here!

Inquire Now

Get All The Latest Research & News!

Our latest content

Get In Front of 1000s of Professionals Today! Advertise Here

Most Popular Articles

Every shirt tells a story—and every story

#ClothingForACause

Science & TechnologyPAPERS

Advertise Here!

Inquire Now

Get All The Latest Research & News!

Our latest content

Get In Front of 1000s of Professionals Today! Advertise Here

Most Popular Articles

Every shirt tells a story—and every story

#ClothingForACause

Science & Technology
PAPERS