ECO: Quantized Training without Full-Precision Master Weights
Paper
•
2601.22101
•
Published
•
6
•
3
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commented on
a paper
6 days ago
ECO: Quantized Training without Full-Precision Master Weights
commented on
a paper
6 days ago
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
commented on
a paper
6 days ago
FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
Organizations
None yet
commented
20
papers
6 days ago
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
Paper
•
2601.22143
•
Published
•
5
•
3
FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
Paper
•
2601.19001
•
Published
•
4
•
3
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
Paper
•
2601.21406
•
Published
•
4
•
4
FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
Paper
•
2601.22146
•
Published
•
8
•
5
Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
Paper
•
2601.22156
•
Published
•
10
•
4
Self-Improving Pretraining: using post-trained models to pretrain better models
Paper
•
2601.21343
•
Published
•
15
•
3
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
Paper
•
2601.21579
•
Published
•
6
•
5
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
Paper
•
2601.21996
•
Published
•
4
•
4
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Paper
•
2601.22054
•
Published
•
5
•
3
One-step Latent-free Image Generation with Pixel Mean Flows
Paper
•
2601.22158
•
Published
•
15
•
3
DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
Paper
•
2601.20975
•
Published
•
9
•
3
Beyond Imitation: Reinforcement Learning for Active Latent Planning
Paper
•
2601.21598
•
Published
•
9
•
4
VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning
Paper
•
2601.22069
•
Published
•
7
•
3
Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report
Paper
•
2601.21051
•
Published
•
12
•
3
MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models
Paper
•
2601.21181
•
Published
•
8
•
3
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
Paper
•
2601.18129
•
Published
•
10
•
4
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
Paper
•
2601.21590
•
Published
•
12
•
13
Discovering Hidden Gems in Model Repositories
Paper
•
2601.22157
•
Published
•
20
•
4
Language-based Trial and Error Falls Behind in the Era of Experience
Paper
•
2601.21754
•
Published
•
16
•
3