2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper
•
2501.00958
•
Published
•
107
SLM e Moe structure PHD tesis: SOTA e valutazione parametri
collezione di paper utili per redazione tesi 1-2-3- capitolo da valutare cambio di rotta e gestione PHD
-
-
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Paper • 2501.01257 • Published • 53 -
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Paper • 2501.01423 • Published • 43 -
REDUCIO! Generating 1024times1024 Video within 16 Seconds using Extremely Compressed Motion Latents
Paper • 2411.13552 • Published -
Generative Modeling with Explicit Memory
Paper • 2412.08781 • Published • 1 -
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
Paper • 2412.16112 • Published • 23 -
TinyFusion: Diffusion Transformers Learned Shallow
Paper • 2412.01199 • Published • 14 -
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
Paper • 2412.12391 • Published • 1 -
ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance
Paper • 2412.06163 • Published -
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Paper • 2411.09702 • Published • 1 -
Four-Plane Factorized Video Autoencoders
Paper • 2412.04452 • Published • 1 -
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
Paper • 2412.10958 • Published • 1 -
Nested Diffusion Models Using Hierarchical Latent Priors
Paper • 2412.05984 • Published -
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
Paper • 2411.06786 • Published -
FlexDiT: Dynamic Token Density Control for Diffusion Transformer
Paper • 2412.06028 • Published -
Phi-4 Technical Report
Paper • 2412.08905 • Published • 119 -
TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
Paper • 2411.15124 • Published • 65 -
Training and Evaluating Language Models with Template-based Data Generation
Paper • 2411.18104 • Published • 3 -
Fox-1 Technical Report
Paper • 2411.05281 • Published • 1 -
ALMA: Alignment with Minimal Annotation
Paper • 2412.04305 • Published -
Training Data for Large Language Model
Paper • 2411.07715 • Published • 1 -
TransformLLM: Adapting Large Language Models via LLM-Transformed Reading Comprehension Text
Paper • 2410.21479 • Published -
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Paper • 2402.14289 • Published • 21 -
TinyLlama: An Open-Source Small Language Model
Paper • 2401.02385 • Published • 95 -
TinyLLM: Learning a Small Student from Multiple Large Language Models
Paper • 2402.04616 • Published -
TinyEmo: Scaling down Emotional Reasoning via Metric Projection
Paper • 2410.07062 • Published • 4 -
LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
Paper • 2408.15881 • Published • 22 -
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
Paper • 2404.04167 • Published • 14 -
Rethinking Optimization and Architecture for Tiny Language Models
Paper • 2402.02791 • Published • 13 -
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Paper • 2312.16862 • Published • 31 -
ProgCo: Program Helps Self-Correction of Large Language Models
Paper • 2501.01264 • Published • 27 -
GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
Paper • 2412.09722 • Published • 5 -
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Paper • 2412.09078 • Published -
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
Paper • 2412.06176 • Published -
MC-NEST -- Enhancing Mathematical Reasoning in Large Language Models with a Monte Carlo Nash Equilibrium Self-Refine Tree
Paper • 2411.15645 • Published • 1 -
PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
Paper • 2412.03578 • Published • 1 -
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Paper • 2411.16579 • Published • 3 -
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 152 -
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 8 -
Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
Paper • 2501.01904 • Published • 34 -
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Paper • 2501.01957 • Published • 48 -
SDPO: Segment-Level Direct Preference Optimization for Social Agents
Paper • 2501.01821 • Published • 20 -
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Paper • 2412.21059 • Published • 18 -
Graph Generative Pre-trained Transformer
Paper • 2501.01073 • Published • 18 -
LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models
Paper • 2501.00874 • Published • 13 -
BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
Paper • 2501.01540 • Published • 6 -
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
Paper • 2404.09785 • Published -
Gemma 2: Improving Open Language Models at a Practical Size
Paper • 2408.00118 • Published • 79 -
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
Paper • 2501.03218 • Published • 37 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 45 -
Test-time Computing: from System-1 Thinking to System-2 Thinking
Paper • 2501.02497 • Published • 46 -
Personalized Graph-Based Retrieval for Large Language Models
Paper • 2501.02157 • Published • 32 -
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Paper • 2501.01830 • Published • 18 -
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
Paper • 2501.02506 • Published • 11 -
Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
Paper • 2403.04801 • Published -
Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison
Paper • 2310.10190 • Published -
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Paper • 2404.06395 • Published • 23 -
LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification
Paper • 2411.19638 • Published • 6 -
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale
Paper • 2411.05045 • Published -
Selecting Between BERT and GPT for Text Classification in Political Science Research
Paper • 2411.05050 • Published -
Improving Bilingual Capabilities of Language Models to Support Diverse Linguistic Practices in Education
Paper • 2411.04308 • Published -
CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
Paper • 2411.08979 • Published -
Introducing Super RAGs in Mistral 8x7B-v1
Paper • 2404.08940 • Published • 2 -
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
Paper • 2407.16741 • Published • 74 -
The GAN is dead; long live the GAN! A Modern GAN Baseline
Paper • 2501.05441 • Published • 94 -
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
Paper • 2501.04377 • Published • 14 -
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Paper • 2501.04003 • Published • 28 -
Entropy-Guided Attention for Private LLMs
Paper • 2501.03489 • Published • 14 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 280 -
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
Paper • 2501.04682 • Published • 99 -
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 92 -
URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics
Paper • 2501.04686 • Published • 53 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 100 -
LLM4SR: A Survey on Large Language Models for Scientific Research
Paper • 2501.04306 • Published • 37 -
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
Paper • 2501.04575 • Published • 24 -
GeAR: Generation Augmented Retrieval
Paper • 2501.02772 • Published • 23 -
Multi-task retriever fine-tuning for domain-specific and efficient RAG
Paper • 2501.04652 • Published • 10 -
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
Paper • 2501.03271 • Published • 10 -
o1-Coder: an o1 Replication for Coding
Paper • 2412.00154 • Published • 45 -
Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers
Paper • 2011.05438 • Published -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 66 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 89 -
WebWalker: Benchmarking LLMs in Web Traversal
Paper • 2501.07572 • Published • 21 -
Transformer^2: Self-adaptive LLMs
Paper • 2501.06252 • Published • 55 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
Demystifying Domain-adaptive Post-training for Financial LLMs
Paper • 2501.04961 • Published • 12 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 295 -
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
Paper • 2501.08187 • Published • 28 -
Diffusion Adversarial Post-Training for One-Step Video Generation
Paper • 2501.08316 • Published • 36 -
FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors
Paper • 2501.08225 • Published • 19 -
OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training
Paper • 2501.08197 • Published • 8 -
Potential and Perils of Large Language Models as Judges of Unstructured Textual Data
Paper • 2501.08167 • Published • 6 -
AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
Paper • 2501.08284 • Published • 7 -
HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
Paper • 2501.08292 • Published • 17 -
MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents
Paper • 2501.08828 • Published • 32 -
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding
Paper • 2501.07783 • Published • 7 -
Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
Paper • 2501.09012 • Published • 10 -
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
Paper • 2501.09019 • Published • 12 -
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 49 -
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Paper • 2501.09732 • Published • 72 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 114 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 106 -
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper • 2501.11873 • Published • 66 -
Reasoning Language Models: A Blueprint
Paper • 2501.11223 • Published • 33 -
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Paper • 2501.17703 • Published • 59 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 36 -
Exploring the sustainable scaling of AI dilemma: A projective study of corporations' AI environmental impacts
Paper • 2501.14334 • Published • 20 -
Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation
Paper • 2501.17749 • Published • 14 -
Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
Paper • 2501.17433 • Published • 9 -
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation
Paper • 2502.01068 • Published • 17 -
NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning
Paper • 2504.13941 • Published • 11
An Empirical Study of Qwen3 Quantization
Paper • 2505.02214 • Published • 25Note utile prendere in considerazione la famiglia Qwen e Deepseek per creare modelli in locale (SLM) SOTA da definire sotto i 13 miliardi di parametri per primo capitolo tesi PHD
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 121Note modello di riferimento per MOE 2025 1 trillione di parametri 32 B per experts