|
Ghost Search — MCP-native, Tor-routed search layer for RAG (seeking research collaborators)
|
|
0
|
27
|
August 21, 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
|
357
|
August 17, 2026
|
|
제목: Weight를 단순한 scalar parameter가 아니라 상태(state)를 가진 객체로 취급하는 학습 구조에 대한 아이디어입니다. 기존 연구가 있을까요?
|
|
5
|
66
|
August 21, 2026
|
|
Same effective batch, different LoRA training time: a small TRL diagnostic
|
|
4
|
97
|
August 19, 2026
|
|
Urgent：Please remove paper 2608.18580 from Daily Papers
|
|
7
|
139
|
August 20, 2026
|
|
Can pull some models, but not others, apparently authorization issue
|
|
2
|
68
|
August 20, 2026
|
|
Is the q_proj/v_proj default worth revisiting? Measurements across four models
|
|
4
|
68
|
August 21, 2026
|
|
Parsewave and the shift toward higher-quality post-training data other than scale?
|
|
1
|
45
|
August 21, 2026
|
|
Project Shadow: A CAPA Can Close Without Fixing Anything (A System for AI and Civic QA)
|
|
1
|
51
|
August 21, 2026
|
|
I have a werid bug with my inference usage credits
|
|
13
|
170
|
August 18, 2026
|
|
Urgent: Please help remove paper 2608.12313, which was submitted by others and is blocking our own Daily Papers submission
|
|
2
|
87
|
August 19, 2026
|
|
Spaces aren't allocating for ZeroGPU tonight
|
|
10
|
187
|
August 15, 2026
|
|
Steer on a Sphere: Geometric Control of Transformer Outputs
|
|
11
|
214
|
August 21, 2026
|
|
UncertaintyGym: A Benchmark for LLM Epistemic Calibration and Uncertainty Expression
|
|
4
|
75
|
August 18, 2026
|
|
Urgent: Please remove withdrawn paper 2608.02738 from Daily Papers
|
|
3
|
140
|
August 17, 2026
|
|
Looking for an Open-Source LLM to Replace Llama 3.3 70B Versatile
|
|
5
|
197
|
August 20, 2026
|
|
Fourier Magnitude KV Cache Quantization
|
|
3
|
92
|
August 20, 2026
|
|
Suppressing unwanted content without negative conditioning, cross-scene consistency in 3DGS, and data-driven artwork placement on generated walls
|
|
3
|
63
|
August 22, 2026
|
|
RAG vs Fine-Tuning: What Are You Actually Using in Production LLM Apps?
|
|
0
|
53
|
August 20, 2026
|
|
Security: Helping
|
|
0
|
28
|
August 20, 2026
|
|
Seeking feedback on token-block context selection for long-sequence QLoRA fine-tuning
|
|
5
|
100
|
August 21, 2026
|
|
Theorem: Advanced AI Systems CAN Be Reliably Aligned and Controlled at Superhuman Levels
|
|
1
|
63
|
August 17, 2026
|
|
An open, model-agnostic "interaction card": verifiable provenance for AI decisions
|
|
8
|
171
|
August 16, 2026
|
|
GlassBallAI: a live, time-locked dataset of Gemini forecasts for studying LLM behaviour
|
|
10
|
280
|
August 19, 2026
|
|
AlphaAvatar v0.6.6: event-driven multimodal memory, unified runtimes, and cleaner agent contracts
|
|
2
|
56
|
August 19, 2026
|
|
Human Vocality Primitives — full preview set now available (17 categories)
|
|
0
|
42
|
August 18, 2026
|
|
Script-Generated Visual Datasets with Reproducible Metadata and Adobe Generator Tools
|
|
1
|
37
|
August 20, 2026
|
|
PIN v2. Choosing a model's size and speed before you train it
|
|
8
|
180
|
August 16, 2026
|
|
I am making a Pyxel gui-based harness with mini-swe-agent
|
|
10
|
195
|
August 16, 2026
|
|
Pending authorship claim and Daily Papers window for arXiv 2608.09209
|
|
2
|
57
|
August 17, 2026
|