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

Aug 6

Submitted by

yxsong

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

·
22 authors

Submitted by

OrlandoHugBot

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

·
15 authors

Submitted by

Jianxiong

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

·
8 authors

Submitted by

zsytony

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

·
11 authors

Submitted by

mizersy

Tool-integrated Reinforcement Learning for Repo Deep Search

·
6 authors

Submitted by

SanghyeokLee

Representation Shift: Unifying Token Compression with FlashAttention

·
6 authors

Submitted by

jiawei-ucas

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

·
9 authors

Submitted by

sikarwarank

The Promise of RL for Autoregressive Image Editing

·
11 authors

Submitted by

Bohan22

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

·
20 authors

3

Submitted by

xxiaoyali

CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

·
5 authors

Submitted by

weijiawu

Multi-human Interactive Talking Dataset

·
3 authors

Submitted by

Jinsong-Li

LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

·
6 authors

Submitted by

Liang-ZX

HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents

·
10 authors

Submitted by

ahnpersie

ChartCap: Mitigating Hallucination of Dense Chart Captioning

·
3 authors

2

Submitted by

AmineAllo

What Is Your AI Agent Buying? Evaluation, Implications and Emerging Questions for Agentic E-Commerce

·
5 authors

Submitted by

amanchadha

AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

·
4 authors

2

Submitted by

chaitanya100100

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

·
6 authors

Submitted by

ikodoh

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

·
5 authors

Submitted by

DanCip

TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs

·
4 authors

2

Submitted by

amanchadha

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

·
3 authors

2

Submitted by

SecureLLMSys

AttnTrace: Attention-based Context Traceback for Long-Context LLMs

·
4 authors