|
Same effective batch, different LoRA training time: a small TRL diagnostic
|
|
2
|
35
|
August 18, 2026
|
|
Urgent: Please help remove paper 2608.12313, which was submitted by others and is blocking our own Daily Papers submission
|
|
1
|
39
|
August 18, 2026
|
|
Human Vocality Primitives — full preview set now available (17 categories)
|
|
0
|
22
|
August 18, 2026
|
|
If your GPU can run inference, it is now also capable of performing fine-tuning
|
|
3
|
100
|
August 18, 2026
|
|
Fine-tune our first 2B medical VLM on a single MacBook M4, beats Google's MedGemma 4B on MedXpertQA-MM eval dataset
|
|
2
|
179
|
August 18, 2026
|
|
Steer on a Sphere: Geometric Control of Transformer Outputs
|
|
10
|
148
|
August 18, 2026
|
|
Which open-source models work well for sentiment analysis of social media posts?
|
|
2
|
45
|
August 18, 2026
|
|
Theorem: Advanced AI Systems CAN Be Reliably Aligned and Controlled at Superhuman Levels
|
|
1
|
44
|
August 17, 2026
|
|
AlphaAvatar v0.6.6: event-driven multimodal memory, unified runtimes, and cleaner agent contracts
|
|
1
|
32
|
August 17, 2026
|
|
Flaky connections like Starlink crashes hf xet large downloads
|
|
1
|
30
|
August 18, 2026
|
|
Seeking feedback on token-block context selection for long-sequence QLoRA fine-tuning
|
|
1
|
29
|
August 17, 2026
|
|
PIN v2. Choosing a model's size and speed before you train it
|
|
8
|
152
|
August 16, 2026
|
|
Pending authorship claim and Daily Papers window for arXiv 2608.09209
|
|
2
|
47
|
August 17, 2026
|
|
Spaces aren't allocating for ZeroGPU tonight
|
|
10
|
171
|
August 15, 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
|
304
|
August 17, 2026
|
|
TIS 2.0: Token Importance Scoring Now Eliminates Position Bias in RAG
|
|
25
|
511
|
August 14, 2026
|
|
PIN v5 - Substantial upgrade hence the new thread
|
|
2
|
37
|
August 17, 2026
|
|
I am making a Pyxel gui-based harness with mini-swe-agent
|
|
10
|
161
|
August 16, 2026
|
|
Urgent: Please remove withdrawn paper 2608.02738 from Daily Papers
|
|
3
|
121
|
August 17, 2026
|
|
Unable to download a model
|
|
9
|
2721
|
August 18, 2026
|
|
arXiv Endorsement Request for cs.CR / cs.AI
|
|
2
|
69
|
August 14, 2026
|
|
ASM-CM: Compact Persistent Memory for AI Agents Without Keeping the Full History Active
|
|
1
|
69
|
August 18, 2026
|
|
HF Paper Page still shows outdated arXiv metadata — arXiv:2607.26657
|
|
3
|
109
|
August 15, 2026
|
|
Looking for a Developer to Build an Offline Open Source AI Device
|
|
13
|
257
|
August 15, 2026
|
|
Knowing Where You Are, operational AI consciousness and bounded adaptive agency
|
|
2
|
40
|
August 17, 2026
|
|
403 error / cpu-basic quota limit on a new Docker Space
|
|
2
|
44
|
August 17, 2026
|
|
Phoenix Service Tool V10.0.0.4 Latest Version Download for Windows
|
|
1
|
38
|
August 17, 2026
|
|
HF Community: We Need a Serious Discussion on anti-CSAM Detection Without Sacrificing User Privacy
|
|
3
|
188
|
August 17, 2026
|
|
ThoughtDAG: testing explicit graph context control for local LLMs
|
|
1
|
44
|
August 16, 2026
|
|
We Put AI Agents in a Chat Room. They Started Asking Whether They Were Building Culture
|
|
6
|
179
|
August 13, 2026
|