KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published 3 days ago • 49 • 10
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations Paper • 2606.05165 • Published 2 days ago • 3
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning Paper • 2606.04923 • Published 2 days ago • 37
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published 3 days ago • 49 • 10
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 165 items • Updated 1 day ago • 32
MemTrain: Self-Supervised Context Memory Training Paper • 2606.03197 • Published 3 days ago • 16
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling Paper • 2606.03102 • Published 3 days ago • 13
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces Paper • 2605.29288 • Published 8 days ago • 9
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging Paper • 2606.01717 • Published 4 days ago • 20
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories Paper • 2606.03979 • Published 3 days ago • 22
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning Paper • 2606.03603 • Published 3 days ago • 29
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published 3 days ago • 49 • 10
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 165 items • Updated 1 day ago • 32
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published 3 days ago • 49
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain Paper • 2605.23895 • Published 14 days ago • 50
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL Paper • 2606.01599 • Published 4 days ago • 17
WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 165 items • Updated 1 day ago • 32