Trending Research
LTX-Video: Realtime Video Latent Diffusion
To address this, our VAE decoder is tasked with both latent-to-pixel conversion and the final denoising step, producing the clean result directly in pixel space.
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information.
Ranked #1 on
Robot Manipulation
on CALVIN
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
To address this, we propose SMoEStereo, a novel framework that adapts VFMs for stereo matching through a tailored, scene-specific fusion of Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) modules.
Language Model Inversion
We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text.
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
xid32/soundmind
•
•
While large language models have shown reasoning capabilities, their application to the audio modality, particularly in large audio-language models (ALMs), remains significantly underdeveloped.
Energy-Based Transformers are Scalable Learners and Thinkers
alexiglad/EBT
•
•
Further, we find that EBTs achieve better results than existing models on most downstream tasks given the same or worse pretraining performance, suggesting that EBTs generalize better than existing approaches.
Do Large Language Models Need a Content Delivery Network?
lmcache/lmcache
•
•
As the use of large language models (LLMs) expands rapidly, so does the range of knowledge needed to supplement various LLM queries.
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
k2-fsa/ZipVoice
•
•
Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters.
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
In a comprehensive evaluation across 28 public benchmarks, our model outperforms Qwen2. 5-VL-7B on nearly all tasks and achieves comparable or even superior performance on 18 benchmarks relative to the significantly larger Qwen2. 5-VL-72B.
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
The era of intelligent agents is upon us, driven by revolutionary advancements in large language models.
