|
Built an LLM steering system, getting weird outputs, need someone to look at it
|
|
0
|
4
|
January 19, 2026
|
|
Fail to claim authorship of the paper arxiv: 2506.00783
|
|
2
|
5
|
January 19, 2026
|
|
AERIS V20 – Architectural Constraints for Non-Standard LLM Behavior
|
|
8
|
99
|
January 19, 2026
|
|
Stylistic Conditioning Dataset with Diffusion Mixture Architecture
|
|
0
|
3
|
January 19, 2026
|
|
Thought Filtering vs. Text Filtering: Empirical Evidence of Latent Space Defense Supremacy Against Adversarial Obfuscation
|
|
3
|
29
|
January 18, 2026
|
|
Do AI models feel?
|
|
90
|
1059
|
January 18, 2026
|
|
Vespa - Custom tokenization in DocumentProcessor - best practices for sending processed tokens to content nodes
|
|
1
|
14
|
January 15, 2026
|
|
Field-specific analyzer chains in Vespa
|
|
1
|
19
|
January 15, 2026
|
|
🚀 Opportunity: Building an AI Agent Marketplace for Dentistry & Healthcare
|
|
3
|
95
|
January 14, 2026
|
|
From AI Blame Games to Forensic Accountability: A Call for Research
|
|
4
|
65
|
January 13, 2026
|
|
Proposal: Overcoming the "Brain-Hand Disconnect" in Manga Generation via Semantic Layout Tags (SMML)
|
|
8
|
131
|
January 13, 2026
|
|
AIphant: An "Aphantasic" Twist on JEPA – Better Generalization via Abstract Latents (No Decoder, Edges + Relations)
|
|
3
|
40
|
January 13, 2026
|
|
Trajectory-Primitive Systems:
|
|
0
|
11
|
January 13, 2026
|
|
Semantic Quantization for Efficient Agent Coordination
|
|
2
|
14
|
January 13, 2026
|
|
Research papers about Muon from MIT
|
|
0
|
26
|
January 10, 2026
|
|
Fail to claim paper authorship
|
|
14
|
720
|
January 9, 2026
|
|
How far before simulation isn't?
|
|
9
|
160
|
January 7, 2026
|
|
Training heritage can matter more than scale in transformer dynamics
|
|
0
|
35
|
January 6, 2026
|
|
A Bidirectional LLM Firewall: Architecture, Failure Modes, and Evaluation Results
|
|
62
|
292
|
January 6, 2026
|
|
Difference between JEPA and Masked Auto Encoders
|
|
2
|
51
|
January 5, 2026
|
|
Fail to claim paper authorship and can't reclaim it
|
|
4
|
101
|
January 3, 2026
|
|
Do you struggle with agent state continuity across restarts?
|
|
0
|
11
|
January 2, 2026
|
|
Quantum Internet Proof-of-Concept: Moonshine Lattice Routing Protocol
|
|
0
|
35
|
January 2, 2026
|
|
Self-Eval + Tool Loops: How LLM Agents Lock Themselves Into Bad States
|
|
0
|
33
|
January 1, 2026
|
|
[cs.CL Endorsement Request] Uniformity Asymmetry: An embedding metric + output-level validation revealing embedding–behavior decoupling
|
|
2
|
40
|
January 1, 2026
|
|
What Theory Does Deep Learning Need? A Measurement and Deployment Perspective
|
|
0
|
20
|
January 1, 2026
|
|
Evidence of latent collapse geometry in frontier LLMs?
|
|
3
|
117
|
December 31, 2025
|
|
Quantifying the "Setup Tax" in Cloud vs WAN Clusters for Iterative Fine-Tuning
|
|
0
|
10
|
December 30, 2025
|
|
Securing Large Vision-Language Models via Deterministic Orchestration Layers
|
|
2
|
35
|
December 30, 2025
|
|
Artificial Ontological Intelligence
|
|
3
|
174
|
December 30, 2025
|