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

Jan 13

Submitted by

Yu2020

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

·
16 authors

Submitted by

taesiri

BabyVision: Visual Reasoning Beyond Language

·
29 authors

Submitted by

reign12

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

stepfun-ai

Submitted by

taesiri

X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests

·
10 authors

Submitted by

yfdeng10

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

DAGroup-PKU

Submitted by

YerbaPage

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

SJTU

Shanghai Jiao Tong University

Submitted by

heroding77

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

ustc

university of science and technology of china

Submitted by

Seongyun

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

kaist-ai

1

Submitted by

zhongzero

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

·
9 authors

Submitted by

zisuh

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

·
11 authors

2

Submitted by

yangzhou99

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

uoft

University of Toronto

Submitted by

Lemoncoke

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

·
18 authors

1

Submitted by

KaiiWuu1993

Boosting Latent Diffusion Models via Disentangled Representation Alignment

Kwai-Kolors

Kolors Team, Kuaishou Technology

Submitted by

Dasool

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

HAERAE-HUB

Submitted by

zhangboguodong

ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration

RUC

Renmin University of China

Submitted by

Yuhan

Forest Before Trees: Latent Superposition for Efficient Visual Reasoning

·
6 authors

1

Submitted by

lixiaoxi45

TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning

·
8 authors

Submitted by

taesiri

Dr. Zero: Self-Evolving Search Agents without Training Data

·
8 authors

Submitted by

zsqzz

OpenTinker: Separating Concerns in Agentic Reinforcement Learning

·
2 authors

Submitted by

deqing

Are LLM Decisions Faithful to Verbal Confidence?

University of Southern California

1

Submitted by

crazyofapple

Structured Episodic Event Memory

Harbin Institute of Technology

Submitted by

Haon-Chen

e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings

·
5 authors

1

Submitted by

imranraad

"TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt

·
2 authors

Submitted by

taesiri

ShowUI-Aloha: Human-Taught GUI Agent

·
8 authors

Submitted by

KomeijiForce

Codified Foreshadowing-Payoff Text Generation

·
5 authors

Submitted by

AmberLJC

Sci-Reasoning: A Dataset Decoding AI Innovation Patterns

orchestra-AI

Orchestra Research

Submitted by

Paipile

Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?

·
3 authors

Submitted by

taesiri

SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language Models

·
7 authors

Submitted by

Akhil-Theerthala

FinForge: Semi-Synthetic Financial Benchmark Generation

gtfintechlab

Financial Services Innovation Lab, Georgia Tech

1

Submitted by

maxma1987

Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths

usc-isi

USC Information Sciences Institute

Submitted by

researchaudio

Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs

·
1 authors

Submitted by

farooqhassaan

FlyPose: Towards Robust Human Pose Estimation From Aerial Views

·
3 authors

1

Submitted by

ymasri

Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification

·
5 authors

Submitted by

amanchadha

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition

·
10 authors

Submitted by

Haonan-Bian

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

·
10 authors

1

Submitted by

SteveZeyuZhang

3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence

PekingUniversity

Peking University

Submitted by

dlion168

On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

·
8 authors

Submitted by

ishikaa

A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality

·
4 authors

Submitted by

amanchadha

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers

·
6 authors