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

Oct 8

Submitted by

AlexiaJM

Less is More: Recursive Reasoning with Tiny Networks

SamsungSAILMontreal

Samsung SAIT AI Lab, Montreal

Submitted by

ZhuofengLi

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Stanford

Submitted by

Ogkunal

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

FractalAIResearch

Fractal AI Research

Submitted by

jiaruz2

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

amazon

Submitted by

WuChengyue

Fast-dLLM v2: Efficient Block-Diffusion LLM

nvidia

Submitted by

weirayao

CoDA: Coding LM via Diffusion Adaptation

Salesforce

Submitted by

AvivNavon

Drax: Speech Recognition with Discrete Flow Matching

aiola-lab

Submitted by

Yuanshi

MixReasoning: Switching Modes to Think

NationalUniversityofSingapore

National University of Singapore

Submitted by

NanHUO

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions

birdsql

Submitted by

LHL3341

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

·
8 authors

Submitted by

domejiraphon

ShapeGen4D: Towards High Quality 4D Shape Generation from Videos

·
8 authors

2

Submitted by

X-iZhang

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

UniversityofGlasgow

University of Glasgow

Submitted by

RyanLiu112

ASPO: Asymmetric Importance Sampling Policy Optimization

·
8 authors

Submitted by

xw-eric

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

ucsbnlp

UC Santa Barbara NLP Group

Submitted by

nielsr

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

4

Submitted by

JohnWeck

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation

UCSC-VLAA

Submitted by

gasolsun

GRACE: Generative Representation Learning via Contrastive Policy Optimization

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

faneggg

Human3R: Everyone Everywhere All at Once

·
6 authors

Submitted by

quicktensor

Scalable In-context Ranking with Generative Models

deepmind

Submitted by

yoavgur

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

tau

Tel Aviv University

Submitted by

taesiri

HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video

·
8 authors

Submitted by

AdamF92

TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation

ReactiveAI

Submitted by

chromeNLP

Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning

·
6 authors

Submitted by

MikaStars39

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?

rednote-hilab

Submitted by

demfier

AInstein: Assessing the Feasibility of AI-Generated Approaches to Research Problems

·
6 authors

Submitted by

taesiri

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

·
8 authors

Submitted by

liuganghuggingface

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

·
4 authors

Submitted by

sirano1004

Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization

·
1 authors

Submitted by

nielsr

Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

MIT

Massachusetts Institute of Technology

Submitted by

taesiri

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation

google

Submitted by

soujanyaporia

Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics

declare-lab

Deep Cognition and Language Research (DeCLaRe) Lab

Submitted by

taesiri

EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark

·
12 authors

Submitted by

amazingj

CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation

DianJin

2

Submitted by

JonasGeiping

Training Dynamics Impact Post-Training Quantization Robustness

·
3 authors

Submitted by

taesiri

Deforming Videos to Masks: Flow Matching for Referring Video Segmentation

·
9 authors

Submitted by

gagan3012

Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models

·
4 authors

Submitted by

rgoswami

Adaptive Pruning for Increased Robustness and Reduced Computational Overhead in Gaussian Process Accelerated Saddle Point Searches

·
2 authors

Submitted by

huangchengchou

Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions

NTHUcc

National Tsing Hua University

2

Submitted by

glory-hyeok

Verifier-free Test-Time Sampling for Vision Language Action Models

kaist-ai

3

Submitted by

rachneetkaur

ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering

·
5 authors

2

Submitted by

minwoosun

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models

·
11 authors

Submitted by

AmberYifan

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

·
8 authors

Submitted by

swzwan

On Code-Induced Reasoning in LLMs

CarnegieMellonCS

Carnegie Mellon University Computer Science

2

Submitted by

ayushzenith

SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation

·
4 authors

Submitted by

Itsuki-music

BACHI: Boundary-Aware Symbolic Chord Recognition Through Masked Iterative Decoding on Pop and Classical Music

UCSD

Submitted by

joaompalmeiro

Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks

·
4 authors

Submitted by

sirano1004

A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling

·
1 authors

2

Submitted by

DarshanDeshpande

MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments

PatronusAI

2

Submitted by

chengyzhao

DYMO-Hair: Generalizable Volumetric Dynamics Modeling for Robot Hair Manipulation

·
7 authors

Submitted by

nazneen

The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models

collinear-ai

Submitted by

lrsbrgrn

HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation

·
4 authors

2