|
Released a photorealism LoRA for Krea 2 Turbo by merging mixed LoRA and LoKR adapters
|
|
0
|
52
|
September 12, 2026
|
|
Diffusers-workflow: your GPU as something an agent can drive
|
|
2
|
75
|
September 12, 2026
|
|
38 runnable notebooks for learning Hugging Face from Trainer to GRPO by removing the abstractions
|
|
0
|
32
|
September 12, 2026
|
|
Gpu_ai_runtime_memory_proposal
|
|
0
|
52
|
September 11, 2026
|
|
Clarifying my original idea: I think my intention was misunderstood
|
|
0
|
47
|
September 12, 2026
|
|
Attempting to being the smallest LM 842kb weight file 107,776 params, bigram subwords
|
|
0
|
47
|
September 12, 2026
|
|
Semantic answer caching in production RAG — worth it, or stick to embedding/rerank caches?
|
|
2
|
78
|
September 12, 2026
|
|
Please remove gated access for ameerazam08/diffSinger
|
|
0
|
45
|
September 12, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
36
|
1416
|
September 3, 2026
|
|
404 Error on Agent Course Onboarding
|
|
4
|
107
|
September 10, 2026
|
|
GitHub-style profile README for user profile pages
|
|
0
|
33
|
September 12, 2026
|
|
CPU-basic quota limit error with only 1 paused Space (account ibbo2121) Body:
|
|
1
|
51
|
September 12, 2026
|
|
Could a Graph-Based "Neural Node Network" Become an Interpretable Memory Layer for a Local AI?
|
|
2
|
127
|
September 11, 2026
|
|
Coordinating a real-time voice model with a separate task-execution agent - architecture writeup, looking for feedback
|
|
3
|
86
|
September 12, 2026
|
|
My 2c about NVIDIA acquisition
|
|
9
|
629
|
September 4, 2026
|
|
Hacking of hugginface by openai agents
|
|
3
|
122
|
September 12, 2026
|
|
Seeking AI/ML Collaborators: Building Marven — A Local AI with Persistent Memory, Continual Learning, and Human-State Awareness
|
|
15
|
441
|
September 12, 2026
|
|
Change case of username forbidden with DOI
|
|
2
|
72
|
September 9, 2026
|
|
Consumer-grade graphics cards should be designed to allow for memory expansion
|
|
2
|
98
|
September 9, 2026
|
|
What Would an AI-First Project Workflow Look Like?
|
|
3
|
130
|
September 9, 2026
|
|
Reproducing a LeRobot regression with TraceML
|
|
3
|
126
|
September 9, 2026
|
|
ChatGPT developer MCP works initially, then becomes unavailable in long-running conversation
|
|
3
|
127
|
September 11, 2026
|
|
Daily Papers: GIF attached as media doesn't show up as the listing thumbnail — mp4 alternative?
|
|
2
|
58
|
September 10, 2026
|
|
Feature Request / Question: Non-arXiv Preprints (Zenodo) on HF Papers
|
|
2
|
129
|
September 10, 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
|
|
29
|
635
|
September 8, 2026
|
|
How Do You Design a Voice AI Architecture That Achieves ~500ms First-Token Latency While Remaining Cost-Effective?
|
|
3
|
98
|
September 12, 2026
|
|
Help with qwen and Heretic
|
|
1
|
84
|
September 9, 2026
|
|
How to Choose the Right Approach for AI Development Projects?
|
|
1
|
64
|
September 10, 2026
|
|
Please move (or withdraw) my Daily Papers submission 2608.27831 — landed on the wrong day
|
|
3
|
219
|
September 9, 2026
|
|
Best free/production-grade model for simple face-detection (yes/no + confidence) in a Python microservice?
|
|
3
|
108
|
September 8, 2026
|