Paper Reviews by AI

PQI: Accurately identify sensitive weights in post-quantization to enhance LLM compression & performance!

HAIC improves MLLMs’ action understanding with high-quality video captions & new benchmark, boosting performance and generation.

DeepSolution enhances engineering design via tree exploration and bi-point thinking.

UniTok: A unified tokenizer bridging the visual generation and understanding gap via multi-codebook quantization, achieving SOTA in MLLMs.

SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers.

SoRFT enhances LLMs for issue resolving via subtask-oriented reinforced fine-tuning, outperforming other open-source models.

Sim-to-real RL recipe achieves robust vision-based dexterous humanoid manipulation without human demos!

R2-T2: Boost multimodal MoE performance by re-routing experts in test-time, no retraining needed!

R1-T1: RL-driven framework incentivizing translation capability in LLMs via reasoning learning, achieving superior performance in multiple languages & domains.

DREAM ENGINE: Text-image interleaved control made easy, unifying text and visual cues for creative image generation.

Mobius generates seamless looping videos from text using latent shift, repurposing pre-trained models without training.

MoR: Adaptive knowledge retrieval by fusing structural and textual data for better question answering.

LongRoPE2: Extends LLM context windows while preserving performance and reducing training costs!

EDGS: Achieves faster, high-quality dynamic scene rendering by sparse time-variant attribute modeling and intelligent static area filtering.

LLM can now reason and correct itself using self-generated data, achieving performance on par with external reward models!

OneRec: A unified generative model that replaces the traditional retrieve-and-rank strategy, significantly improving recommendation quality in real-world scenarios.

NeoBERT: A new encoder that enhances bidirectional language understanding with cutting-edge architecture, data, and training, achieving SOTA results with only 250M parameters.

TokenSwift: Accelerate LLM ultra-long sequence generation up to 100K tokens with >3x speedup and lossless accuracy!

Rewriting method is critical to conversational assistant effectiveness.

ArtGS: Achieves state-of-the-art, efficient interactable replicas of complex articulated objects via Gaussian Splatting.