SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
Paper • 2506.12935 • Published • 2
Soroush Vosoughi
soroushv
·
AI & ML interests
Large Language Models
Prosocial NLP
Computational Social Science
Recent Activity
authored a paper about 5 hours ago
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models authored a paper about 5 hours ago
Communication is All You Need: Persuasion Dataset Construction via
Multi-LLM Communication authored a paper about 5 hours ago
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal UnderstandingOrganizations
authored 6
papers about 5 hours ago
Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication
Paper • 2502.08896 • Published
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
Paper • 2502.06020 • Published
Superficial Self-Improved Reasoners Benefit from Model Merging
Paper • 2503.02103 • Published
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 27
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 337
upvoted a paper about 13 hours ago
authored a
paper 8 months ago
authored 7
papers 10 months ago
SimVLG: Simple and Efficient Pretraining of Visual Language Generative Models
Paper • 2310.03291 • Published • 1
A Survey of Data Augmentation Approaches for NLP
Paper • 2105.03075 • Published
Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
Paper • 2307.07063 • Published
Knowledge Infused Decoding
Paper • 2204.03084 • Published
Contrastive Learning for Prompt-Based Few-Shot Language Learners
Paper • 2205.01308 • Published • 1
Language Models are Multilingual Chain-of-Thought Reasoners
Paper • 2210.03057 • Published • 1
Mind's Eye: Grounded Language Model Reasoning through Simulation
Paper • 2210.05359 • Published • 1
upvoted a paper over 1 year ago
authored a
paper almost 3 years ago