research

Loss Smoothing for Stable Adaptation Under Distribution Shift

arXiv:2607.00634v1 Announce Type: cross Abstract: In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift. Standard adaptation methods ty

Low Perplexity is Repetition: A One-Dimensional Self-Conditioning Attractor in Continuous Diffusion LMs

DGX agent

arXiv:2607.00588v1 Announce Type: new Abstract: Continuous diffusion language models such as ELF report record-low generative perplexity (Gen-PPL). We find a catch: these models repeat far more than h

researcharxiv-cs-cl

2 Jul 2026

LRAT-Catcher: Importing SAT Solver Certificates into Lean4 by Reflection

arXiv:2607.00815v1 Announce Type: cross Abstract: SAT solvers settle combinatorial problems beyond the reach of interactive theorem provers and produce LRAT certificates for independent verification.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

arXiv:2602.05275v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various

Measuring the Gap Between Human and LLM Research Ideas

arXiv:2607.01233v1 Announce Type: cross Abstract: LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert pre

Memory-Native Non-Terrestrial Networks for Embodied Intelligence

arXiv:2607.00029v1 Announce Type: cross Abstract: Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resourc

MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers

researchapple-ml-research

Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associa

Message Passing Enables Efficient Reasoning

arXiv:2607.01077v1 Announce Type: new Abstract: While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is

researcharxiv-cs-cl

MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors

arXiv:2607.00848v1 Announce Type: new Abstract: In this opinion paper, we propose MetaHOPE, an error severity-aware annotation framework for evaluating metaphor translations. Metaphors present challen

researcharxiv-cs-cl

MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization

arXiv:2607.00902v1 Announce Type: new Abstract: Driven by Artificial Intelligence-Generated Content (AIGC), the authenticity of audio-visual content is facing severe challenges. Temporal Forgery Local

MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration

arXiv:2607.00138v1 Announce Type: new Abstract: MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, an

MineRobot: An Actuator-Centered Kinematic Modeling and Solving Framework for Underground Mining Robots

arXiv:2603.22055v2 Announce Type: replace-cross Abstract: Underground mining robots are increasingly modeled for planning, operator training, and digital-twin workflows, where reliable actuator-level

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

arXiv:2601.11641v3 Announce Type: replace Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by th

Moire Video Authentication: A Physical Signature Against AI Video Generation

arXiv:2604.01654v2 Announce Type: replace-cross Abstract: Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a phy

MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation

arXiv:2511.19326v2 Announce Type: replace Abstract: Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. Whil

Multi-Embodiment Robotic Retargeting via Guided Diffusion Model

arXiv:2505.20857v2 Announce Type: replace Abstract: Motion retargeting for specific robot from existing motion datasets is one critical step in transferring motion patterns from human behaviors to and

MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints

arXiv:2607.00273v1 Announce Type: new Abstract: The core challenge in multi-view pedestrian detection (MVPD) lies in effective aggregation of visual features from different viewpoints for robust occlu

Neural Certificate Pricing for Combinatorial Optimization Problems

arXiv:2607.01185v1 Announce Type: new Abstract: Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search. One needs to search over the s

NoPA: Non-Parametric Online 3D Scene Graph Generation

arXiv:2607.00529v1 Announce Type: new Abstract: Classic 3D scene graph generation approaches fail to work in real-time due to the heavy computational cost of environment mapping and the need to genera

On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

researchapple-ml-research

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision language models (VLMs). Wh

OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization

arXiv:2607.00289v1 Announce Type: new Abstract: Temporal Action Localization (TAL) typically relies on segment annotations or offline access to full videos, limiting scalability and online use. We int

Oops, SIGReg did it again! Large scale (CC12M->Datacomp-L) vision-language JEPA pretraining beats CLIP and SigLIP objectives! Thanks to SIGR…

Oops, SIGReg did it again! Large scale (CC12M->Datacomp-L) vision-language JEPA pretraining beats CLIP and SigLIP objectives! Thanks to SIGReg, our LeVLJEPA has no collapse, no EMA, no stop-gradient,

researchyann-lecun--x

OpFML: Pipeline for ML-based Operational Inference

arXiv:2601.11046v2 Announce Type: replace Abstract: Machine learning models for climate and Earth science are becoming increasingly capable, yet model deployment into operational use remains a largely

Optimal any-angle path planning in static and dynamic environments

arXiv:2607.00065v1 Announce Type: cross Abstract: Any-angle path planning extends traditional graph-based path planning by allowing movement between any pair of vertices, rather than being restricted

Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates

arXiv:2503.24075v4 Announce Type: replace-cross Abstract: Low-rank optimization problems with sparse simplex constraints involve variables that must satisfy nonnegativity, sparsity, and sum-to-1 condi

PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding

arXiv:2512.20907v2 Announce Type: replace Abstract: 3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reas

Path Planning in Physically Viable World Models

arXiv:2607.00673v1 Announce Type: new Abstract: Robots deployed in unstructured outdoor environments often plan from scene reconstructions collected before deployment because operators cannot remap la

Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions

arXiv:2607.00937v1 Announce Type: new Abstract: Persona-driven generations (PDGs) have seen prolific use in research and industry applications, where a large language model (LLM) takes on a 'persona'

researcharxiv-cs-cl

PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks

arXiv:2504.02839v2 Announce Type: replace-cross Abstract: Proteins move and deform to ensure their biological functions. Despite significant progress in protein structure prediction, approximating con

Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences

arXiv:2607.00738v1 Announce Type: cross Abstract: Large language models can generate polished scientific text that includes unsupported claims, allowing hallucinations to enter the archival record. As

Play Like Champions: Counterfactual Feedback Generation in Latent Space

arXiv:2607.00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games. As a byproduct, researchers have b

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption

arXiv:2607.00012v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, effectively mitigating their inherent

Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

arXiv:2607.00472v1 Announce Type: cross Abstract: Cardiovascular disease is still one of the main causes of death around the world. Acute myocardial infarction (MI), or heart attack, claims millions o

[Preprint] Dynamic Modeling, Gait Synthesis, and Control of a Novel Subsurface Bore Propagator

arXiv:2607.00569v1 Announce Type: new Abstract: In this article, we present dynamic modeling, gait synthesis, and feedback control design for a modular novel subsurface robot, designed for human-free

PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

arXiv:2607.00176v1 Announce Type: new Abstract: We introduce PRISM-VO, a novel pure optimization-based sparse photometric visual odometry framework for focused plenoptic cameras. The core of PRISM-VO

Program Manager (RSI Lab) https://sakana.ai/careers/program-manager-rsi-lab/

Sakana AI is hiring a Program Manager for its RSI (Research and Systems Integration) Lab, as posted on their careers page. The role likely involves managing research initiatives, coordinating between

researchdavid-ha--x

Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video

arXiv:2607.00157v1 Announce Type: new Abstract: Reconstructing 4D animals from monocular videos is challenging due to large inter-species variation, complex articulations, and the lack of reliable tem

Prototype Memory-Guided Training-Free Anomaly Classification and Localization in Prenatal Ultrasound

arXiv:2607.00744v1 Announce Type: cross Abstract: Prenatal anomaly classification and localization is of critical importance for fetal health and pregnancy management. Although ultrasound (US) is the

QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding

arXiv:2607.00983v1 Announce Type: new Abstract: Video understanding is often plagued by severe temporal redundancy, where processing dense frame sequences is both semantically inefficient and computat

Quadratic Programming Approach for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games

arXiv:2509.25618v2 Announce Type: replace-cross Abstract: There has been significant recent progress in algorithms for approximation of Nash equilibrium in large two-player zero-sum imperfect-informat

Quantitative Understanding of PDF Fits and their Uncertainties

arXiv:2512.24116v3 Announce Type: replace-cross Abstract: Parton Distribution Functions (PDFs) play a central role in describing experimental data at colliders and provide insight into the structure o

Reading Order Inference for Complex Document Layouts

arXiv:2607.01018v1 Announce Type: cross Abstract: Reading order inference remains a critical bottleneck in the digitization of complex historical manuscripts, where pages contain multiple spatially in

Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning

arXiv:2511.02644v2 Announce Type: replace Abstract: We study computable probably approximately correct (CPAC) learning, where learners are required to be computable functions. It had been previously o

Relation-Centric Open-Vocabulary 3D Gaussian Segmentation

arXiv:2607.01140v1 Announce Type: new Abstract: Open-vocabulary 3D Gaussian segmentation is challenging because it requires language understanding for diverse queries and accurate separation of Gaussi

Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

arXiv:2607.00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how t

Residual Context Diffusion Language Models

researchapple-ml-research

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art

Rethinking Robust Adversarial Concept Erasure in Diffusion Models

arXiv:2510.27285v4 Announce Type: replace Abstract: Concept erasure methods aim to remove specific unsafe target concepts in diffusion models while preserving image generation utility. To address the

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

arXiv:2603.21573v2 Announce Type: replace Abstract: Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive