new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Sep 10

Submitted by

benfielding

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Gensyn

Submitted by

Hanyuezhuohua

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

tencent

Submitted by

taesiri

Visual Representation Alignment for Multimodal Large Language Models

·
13 authors

Submitted by

taesiri

Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

·
6 authors

Submitted by

sanaka87

Reconstruction Alignment Improves Unified Multimodal Models

·
4 authors

Submitted by

taesiri

Language Self-Play For Data-Free Training

·
5 authors

Submitted by

JasperHaozhe

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

·
6 authors

Submitted by

aopolin-lv

F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

·
10 authors

Submitted by

fenfan

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

·
6 authors

Submitted by

thughost

Causal Attention with Lookahead Keys

·
4 authors

Submitted by

xianbao

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

·
9 authors

Submitted by

taesiri

SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

·
5 authors

Submitted by

ChillingDream

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

·
11 authors

Submitted by

hzy46

ΔL Normalization: Rethink Loss Aggregation in RLVR

·
5 authors

Submitted by

nfrumkin

Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

·
2 authors

Submitted by

PraneetNeuro

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers

·
5 authors

2

Submitted by

cdancette

Curia: A Multi-Modal Foundation Model for Radiology

·
23 authors

Submitted by

jfkback

Benchmarking Information Retrieval Models on Complex Retrieval Tasks

·
2 authors