new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Oct 9

Submitted by

Dominic789654

LongGenBench: Long-context Generation Benchmark

·
4 authors

Submitted by

shizhuo2

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

·
3 authors

Submitted by

leonardPKU

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

·
10 authors

Submitted by

DonJoey

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

·
12 authors

Submitted by

wenlinyao

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

·
6 authors

Submitted by

wondervictor

ControlAR: Controllable Image Generation with Autoregressive Models

·
9 authors

Submitted by

yuezrhb

Inference Scaling for Long-Context Retrieval Augmented Generation

·
10 authors

Submitted by

JackFram

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

·
5 authors

Submitted by

garyzhao9012

$ε$-VAE: Denoising as Visual Decoding

·
9 authors

Submitted by

WHB139426

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

·
9 authors

Submitted by

yuyijiong

Hyper-multi-step: The Truth Behind Difficult Long-context Tasks

·
1 authors

Submitted by

cyk1337

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

·
6 authors

Submitted by

dalime

EBES: Easy Benchmarking for Event Sequences

·
5 authors