arXiv ·
AliO: Output Alignment Matters in Long-Term Time Series Forecasing
Public paper from arXiv. Open the source to read the full record.
Home / Browse
Models & research
Examine models, papers and evaluations with their methods and limitations.
802 public stories
arXiv ·
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?
Public paper from arXiv. Open the source to read the full record.
arXiv ·
LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
Public paper from arXiv. Open the source to read the full record.
arXiv ·
TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Open-ended Scientific Discovery with Possibilistic Reasoning
Public paper from arXiv. Open the source to read the full record.
量子位 ·
清华具身模型登顶全球第一！突围GPT-6、英伟达，不靠外挂和额外数据
Public article from 量子位. Open the source to read the full record.
量子位 ·
不等Gemini 4了！谷歌发布办公Agent，支持调用Claude
Public article from 量子位. Open the source to read the full record.
Hugging Face ·
Introducing Falcon ASR
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
Public article from Hugging Face. Open the source to read the full record.
Hacker News ·
Evaluating Memory Structure in LLM Agents
Submitted by matt_d. Hacker News recorded 1 points and 0 comments as of Nov 3, 2026 (UTC).
OpenAI ·
A model guide for the GPT-6 family
Public article from OpenAI. Open the source to read the full record.
Hugging Face ·
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
Public article from Hugging Face. Open the source to read the full record.
OpenAI ·
Introducing GPT-6.1 Sol
Public article from OpenAI. Open the source to read the full record.
MIT News ·
The effects of an “algorithmic monoculture” depend on the details
In a study focusing on hiring decisions, MIT researchers found the use of a single algorithm by many firms could benefit job seekers in certain situations.
Hacker News ·
A-Mem: Agentic Memory for LLM Agents
Submitted by jerlendds. Hacker News recorded 2 points and 0 comments as of Oct 26, 2026 (UTC).
Hugging Face ·
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
BenchMIRT: What are LLM benchmarks actually measuring?
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
Public article from Hugging Face. Open the source to read the full record.
Hacker News ·
LeRobot: An Open-Source Library for End-to-End Robot Learning
Submitted by nill0. Hacker News recorded 2 points and 0 comments as of Nov 5, 2026 (UTC).
Hacker News ·
Robot Learning: A Tutorial
Hacker News recorded 2 points and 0 comments as of Oct 11, 2026 (UTC).