What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility
Paper • 2606.21126 • Published
Yuren Hao
blackhao0426
·
AI & ML interests
NLP & Biologically plausible learning & Foundation models & Learning dynamics
Recent Activity
authored a paper 3 days ago
VGI-Bench: Probing Visual Intelligence in Video Generation Models authored a paper 3 days ago
User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented InteractionOrganizations
authored 4
papers 3 days ago
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Paper • 2608.19583 • Published • 171
User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
Paper • 2603.20939 • Published
An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
Paper • 2508.08833 • Published
upvoted 2
papers 3 days ago
updated a
model about 2 months ago
published a
model about 2 months ago
updated a
model 2 months ago
published a
model 2 months ago
liked a
dataset 3 months ago
updated 3
models 4 months ago
published 3
models 4 months ago
updated a
dataset 5 months ago
published a
dataset 5 months ago
updated a
dataset 5 months ago