Sergey Bratchikov

hivaze's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 20 papers about 19 hours ago

Number it: Temporal Grounding Videos like Flipping Manga

Paper • 2411.10332 • Published 6 days ago • 12

Evaluating the role of `Constitutions' for learning from AI feedback

Paper • 2411.10168 • Published 6 days ago • 5

SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning

Paper • 2411.10161 • Published 6 days ago • 6

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities

Paper • 2410.02155 • Published Oct 3 • 2

Analyzing The Language of Visual Tokens

Paper • 2411.05001 • Published 14 days ago • 20

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Paper • 2411.04986 • Published 14 days ago • 5

DELIFT: Data Efficient Language model Instruction Fine Tuning

Paper • 2411.04425 • Published 15 days ago • 9

Balancing Pipeline Parallelism with Vocabulary Parallelism

Paper • 2411.05288 • Published 14 days ago • 19

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Paper • 2411.06176 • Published 12 days ago • 44

Direct Preference Optimization Using Sparse Feature-Level Constraints

Paper • 2411.07618 • Published 10 days ago • 15

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Paper • 2411.09595 • Published 7 days ago • 65

Adaptive Decoding via Latent Preference Optimization

Paper • 2411.09661 • Published 7 days ago • 10

Top-nσ: Not All Logits Are You Need

Paper • 2411.07641 • Published 10 days ago • 15

Drowning in Documents: Consequences of Scaling Reranker Inference

Paper • 2411.11767 • Published 3 days ago • 16

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering

Paper • 2411.11504 • Published 3 days ago • 16

ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements

Paper • 2411.12044 • Published 3 days ago • 12

LLM Pruning and Distillation in Practice: The Minitron Approach

Paper • 2408.11796 • Published Aug 21 • 55

Scalable Autoregressive Image Generation with Mamba

Paper • 2408.12245 • Published Aug 22 • 25

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments

Paper • 2408.10945 • Published Aug 20 • 8

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

Paper • 2408.14468 • Published Aug 26 • 35