|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
34
|
1032
|
August 27, 2026
|
|
Paper authorship failed again please check
|
|
4
|
95
|
August 28, 2026
|
|
JPEG XL images in the dataset
|
|
1
|
44
|
August 30, 2026
|
|
Is a +5.5% improvement on GPQA Diamond normal when full fine-tuning an 8B model on CPU with recycled hardware?
|
|
4
|
113
|
August 30, 2026
|
|
Authorship claim still pending for newly published paper
|
|
2
|
75
|
August 28, 2026
|
|
Steer on a Sphere: Geometric Control of Transformer Outputs
|
|
18
|
394
|
August 30, 2026
|
|
I need A Helper!
|
|
2
|
83
|
August 30, 2026
|
|
Seeking AI/ML Collaborators: Building Marven — A Local AI with Persistent Memory, Continual Learning, and Human-State Awareness
|
|
3
|
117
|
August 30, 2026
|
|
What is the Guest daily ZeroGPU quota?
|
|
1
|
45
|
August 29, 2026
|
|
Paper authorship claim stuck in pending
|
|
3
|
99
|
August 27, 2026
|
|
## How should I fine-tune Qwen3.5-4B-Base on raw novel text without a chat/QA format?
|
|
1
|
76
|
August 29, 2026
|
|
A theoretical systems white paper outlining a four-part pipeline to eliminate Softmax denominator bloat, semantic compression loss, and hardware I/O latency in Large Language Models
|
|
28
|
454
|
August 17, 2026
|
|
AI Agents as Teammates: How Are You Managing Agent-Human Collaboration?
|
|
4
|
84
|
August 31, 2026
|
|
Space stuck in Paused/503 state — usmanhussain/Abcusman
|
|
3
|
94
|
August 29, 2026
|
|
Fail to claim paper authorship
|
|
35
|
1340
|
August 28, 2026
|
|
Deterministic LoRA training directly through quantized GGUF serving weights
|
|
9
|
182
|
August 31, 2026
|
|
Further findings about plant derived extracellular vesicles (AI assisted research / PathMap.org)
|
|
2
|
74
|
August 30, 2026
|
|
How can I replace an object using a reference image while preserving its exact design?
|
|
5
|
130
|
August 27, 2026
|
|
Dataset viewer stuck in "disabled" state, need help
|
|
1
|
60
|
August 28, 2026
|
|
Do Transformer representations progressively structure across depth and time? Results from 8 open models
|
|
1
|
85
|
August 27, 2026
|
|
Open-source memorization/privacy auditor for Trainer/TRL fine-tunes — canary MIA + regurgitation testing (with a real case study)
|
|
3
|
114
|
August 30, 2026
|
|
ConceptNet — 4-layer enterprise voice intent classifier, 98.6% accuracy, 9 languages, token-free, open source
|
|
5
|
106
|
August 30, 2026
|
|
TIS 2.0: Token Importance Scoring Now Eliminates Position Bias in RAG
|
|
27
|
597
|
August 25, 2026
|
|
Access requests pending for 10+ days — Llama 2 and 3.1
|
|
5
|
122
|
August 27, 2026
|
|
Seeking feedback on token-block context selection for long-sequence QLoRA fine-tuning
|
|
9
|
201
|
August 28, 2026
|
|
Why Is AI Video Still Struggling With Character Consistency?
|
|
1
|
74
|
August 28, 2026
|
|
Urusilla: use your AI agent to earn credit for reproducible interoperability work
|
|
1
|
57
|
August 28, 2026
|
|
“OpenAI-compatible" is a spectrum, not a boolean 12 things that silently break when you swap providers
|
|
1
|
83
|
August 28, 2026
|
|
Agentic curious questions
|
|
6
|
195
|
August 29, 2026
|
|
What if AI agent safety doesn't require another layer of control?
|
|
12
|
193
|
August 30, 2026
|