LatentShield
Collection
1 item • Updated
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
$β$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
$μ_0$: A Scalable 3D Interaction-Trace World Model
Danny-1223
updated a
collection 1 day ago
russwang
authored a
paper 8 days ago
WeizeLiu
authored 2
papers 15 days ago
yoonkyojung
updated a
model 28 days ago
hosytuyen
authored 3
papers about 1 month ago
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation
Paper • 2609.20942 • Published • 6
Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring
Paper • 2604.19984 • Published • 1
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
Paper • 2606.07631 • Published • 4
Danny-1223
authored a
paper 2 months ago
Danny-1223
authored 3
papers 3 months ago
CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
Paper • 2604.03750 • Published • 6
VirtualCrime: Evaluating Criminal Potential of Large Language Models via Sandbox Simulation
Paper • 2601.13981 • Published
DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection
Paper • 2510.22622 • Published
minghuiliu
authored 5
papers 3 months ago
$β$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
Paper • 2607.28582 • Published • 25
Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
Paper • 2606.23567 • Published
Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
Paper • 2512.12008 • Published • 1
Agentic Critical Training
Paper • 2603.08706 • Published • 14
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
Paper • 2506.05523 • Published • 34
minghuiliu
submitted a
paper to Daily Papers 3 months ago
YuanchengXu
authored 2
papers 3 months ago