|
What can silently go wrong between an SFT JSONL file and the loss tensor?
|
|
2
|
61
|
November 5, 2026
|
|
A compass gate for self-updating models: learn by day, consolidate by night
|
|
3
|
70
|
November 6, 2026
|
|
Terse abstention qwen 3 4B
|
|
2
|
35
|
November 6, 2026
|
|
Tightening a definition I posted here loosely in July: "summarization bias" now has a registered falsifier — please try to break the protocol
|
|
11
|
169
|
November 6, 2026
|
|
Six browser-only writing tools (emotion-label and simile flags, sentence-length distribution) — looking for false positives
|
|
2
|
35
|
November 6, 2026
|
|
Seeking Independent Reviewers: Wheat Rust AI Cross-Dataset Generalisation
|
|
3
|
33
|
November 6, 2026
|
|
Which chat SDK is good for adding chat and video calling to one app?
|
|
4
|
69
|
November 6, 2026
|
|
Sol0mon – Exploring multi-agent AI engineering and decision verification
|
|
11
|
130
|
November 6, 2026
|
|
Roadmap for AI learning preparation
|
|
4
|
234
|
November 4, 2026
|
|
Tokenizer fairness for Urdu: 5.39× more tokens on GPT-2, 2.72× on Qwen2.5
|
|
2
|
51
|
November 6, 2026
|
|
Can we prove this: the code submitted with this research paper actually produced the numbers reported?
|
|
19
|
346
|
November 5, 2026
|
|
Ifparse 2.0 Release
|
|
2
|
122
|
November 4, 2026
|
|
QWEN Malicious Intent Forensics Investigation
|
|
5
|
123
|
November 4, 2026
|
|
Non-parametric Rmsnorm with Normuon
|
|
1
|
47
|
November 4, 2026
|
|
Seeking Guidance on Custom USD Robot Simulation, Wheel Traction, and Physics Validation in NVIDIA Isaac Sim 6.1
|
|
1
|
47
|
November 3, 2026
|
|
How do you keep project context next to the model experiments you run?
|
|
1
|
37
|
November 6, 2026
|
|
The Infallible Bureaucrat: where does judgment go when we govern agents?
|
|
1
|
37
|
November 4, 2026
|
|
Remote MCP server OAuth token exchange returns HTTP 500 after authorization — is this a known server-side issue?
|
|
1
|
34
|
November 4, 2026
|
|
Issue with arXiv Paper Indexing on Hugging Face Papers
|
|
14
|
299
|
November 4, 2026
|
|
My First 1B transformer model trained from scratch has published
|
|
5
|
170
|
November 5, 2026
|
|
QLoRA on a code-repair dataset: eval loss rises after epoch 1 even with 2× more data. Early stopping, or mask the copied tokens?
|
|
3
|
64
|
November 3, 2026
|
|
OpenAMRobot 2.0: open-source dual-arm mobile manipulator for imitation learning (OpenArm 2.0 on a lift)
|
|
2
|
84
|
November 3, 2026
|
|
ScopeHaven: check what an agent did in your app, not what it said (Apache-2.0)
|
|
3
|
41
|
November 5, 2026
|
|
Request to withdraw my Daily Papers submission for arXiv:2610.35497
|
|
1
|
34
|
November 4, 2026
|
|
Paper indexing fails for arXiv:2610.37257 (GameVerse)
|
|
2
|
47
|
November 4, 2026
|
|
Testing Agaram (Tamil model) on Sri Lankan vs. Tamil Nadu Tamil
|
|
2
|
49
|
November 5, 2026
|
|
Introducing Hierarchos-Native: A Rust + Vulkan Backend for Transformer Training and Inference on Consumer GPUs 💜
|
|
0
|
28
|
November 4, 2026
|
|
How to evaluate deceptive dialogue in LLM-based NPCs?
|
|
12
|
329
|
November 2, 2026
|
|
Feedback on an invoice-to-Excel pipeline that flags uncertain values instead of guessing
|
|
1
|
36
|
November 5, 2026
|
|
“2026 US Midterms Forecasting Experiment.”
|
|
58
|
921
|
November 5, 2026
|