Search: “research”

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

arXiv:2608.11408v1 Announce Type: new Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge is no lon

Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes

DGX agent

arXiv:2608.11390v1 Announce Type: new Abstract: Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value. This

researcharxiv-cs-lg

13 Aug 2026

New Orthogonal Multiwavelet Filters Derived by Matrix Spectral Factorization

arXiv:2608.11518v1 Announce Type: new Abstract: The paper considers the construction of two new orthogonal multiwavelets with supercompact support by using the Fast Bauer's method for matrix spectral

On Benchmarking Human-Like Intelligence in Machines

arXiv:2502.20502v2 Announce Type: replace Abstract: Recent advances in Artificial Intelligence (AI) have yielded powerful computational models that, by learning from vast amounts of human-generated da

On Data-Driven Koopman Representations of Nonlinear Delay Differential Equations

arXiv:2604.03086v2 Announce Type: replace-cross Abstract: This work establishes a rigorous bridge between infinite-dimensional delay dynamics and finite-dimensional Koopman learning, with explicit and

On Weak Bisimilarities in CCSK

arXiv:2608.11531v1 Announce Type: new Abstract: In the context of CCSK, a reversible extension of CCS, we study different notions of bisimilarity (strong/weak, forward-only/reversible) and highlight t

PolarSym: Polar Geometry-aware Attention for CAD Floorplan Parsing

arXiv:2608.11793v1 Announce Type: new Abstract: CAD plan parsing is a fundamental task in Building Information Modeling (BIM), aiming to automatically extract architectural elements including walls, d

Probably Approximately Correct Maximum A Posteriori Inference

arXiv:2601.16083v2 Announce Type: replace-cross Abstract: Computing the conditional mode of a distribution, better known as the maximum a posteriori (MAP) assignment, is a fundamental task in probabil

Probing and steering biology across Boltz-1s trunk-diffusion boundary

arXiv:2608.11475v1 Announce Type: cross Abstract: AlphaFold3-class structure predictors pair a representational trunk, which processes sequence and context, with a diffusion module, which generates at

Proportional Analogies on Probability Distributions via Bayesian Updating

arXiv:2608.11724v1 Announce Type: new Abstract: Analogies are quaternary relations of the form 'A is to B as C is to D'. Among the various formalizations of analogical reasoning, proportional analogie

ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT Object Detection

arXiv:2608.11595v1 Announce Type: new Abstract: RGB-Thermal (RGBT) object detection enables robust perception in complex scenes by leveraging the complementary strengths of visible textures and therma

QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving

arXiv:2608.12121v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting

arXiv:2608.12251v1 Announce Type: cross Abstract: Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training. This paper asks whe

Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs

arXiv:2608.11573v1 Announce Type: cross Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LL

RelShap: Relationally Consistent Shapley Explanations

arXiv:2608.11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints. Widely used Shapley va

Remote Sensing and Machine Learning-Based Analysis of Land Use and Vegetation Change in Dhaka District, Bangladesh

arXiv:2608.12001v1 Announce Type: cross Abstract: Rapid urbanization in Dhaka District, Bangladesh has triggered substantial alterations in land use and environmental conditions, necessitating systema

Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

arXiv:2608.11742v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substant

Robustness of AI-Art Detectors under Generator Shift

arXiv:2608.11643v1 Announce Type: new Abstract: Text-to-image generative models have advanced rapidly, with modern Diffusion Transformer architectures producing images that are increasingly difficult

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

arXiv:2608.12099v1 Announce Type: cross Abstract: We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectu

Sakana Chat just got a big upgrade. No login required, free to use: https://chat.sakana.ai/ Powered by Fugu and Namazu, our Japanese LLM. Wi…

Sakana Chat just got a big upgrade. No login required, free to use: https://chat.sakana.ai/ Powered by Fugu and Namazu, our Japanese LLM. With newly added code execution, you can vibe-code interactive

researchdavid-ha--x

SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting

arXiv:2601.04348v2 Announce Type: replace Abstract: Recent advances in 3D Gaussian Splatting have allowed for real-time, high-fidelity novel view synthesis. Nonetheless, these models have significant

SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward

arXiv:2608.12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to c

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

arXiv:2608.12219v1 Announce Type: new Abstract: Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because

Seed2GS: Camera-Free, Training-Free Object Extraction from 3D Gaussian Scenes via a Single Reference-View Grounding

arXiv:2608.11928v1 Announce Type: new Abstract: Extracting a target object from a pre-built 3D Gaussian Splatting (3DGS) scene enables interactive 3D editing. Existing methods either train for tens of

Soft-Attention Improves Skin Cancer Classification Performance

arXiv:2105.03358v4 Announce Type: replace-cross Abstract: In clinical applications, neural networks must focus on and highlight the most important parts of an input image. Soft-Attention mechanism ena

SportD: How do VLMs physically strategize?

arXiv:2607.14616v3 Announce Type: replace Abstract: Vision-language models (VLMs) can describe a scene, but can they act well within one? We study whether VLMs can make sound strategic decisions, usin

STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding

arXiv:2608.11699v1 Announce Type: new Abstract: Constructing a unified 3D scene understanding model has long been hindered by the topological discrepancies across sensor modalities. While applying the

Strengthening Full Justified Representation: Efficient Verification and Computation

arXiv:2608.11500v1 Announce Type: cross Abstract: Full justified representation (FJR) is among the strongest known satisfiable proportionality axioms for approval-based committee elections. Recent wor

Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures

arXiv:2608.11255v1 Announce Type: new Abstract: Accurate prediction of vapor--liquid equilibrium (VLE) for hydrocarbon-nitrogen mixtures remains challenging for cubic equations of state, particularly

Task- and dataset-specific information in protein language models

arXiv:2608.12090v1 Announce Type: new Abstract: Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on

TC-Pade: Trajectory-Consistent Pade Approximation for Diffusion Acceleration

arXiv:2603.02943v2 Announce Type: replace Abstract: Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative samp

TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning

arXiv:2608.11820v1 Announce Type: new Abstract: Visual data is typically a prerequisite for training existing video anomaly detection (VAD) methods. However, obtaining sufficient annotated anomaly dat

TELLME: Test-Enhanced Learning for Language Model Enrichment

arXiv:2608.11788v1 Announce Type: cross Abstract: Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been ac

Terminal Symmetry as a Decision Resource: Statewise Refinement for Anytime Verified Construction

arXiv:2608.11318v1 Announce Type: cross Abstract: Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent. We develop a dec

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

arXiv:2608.11970v1 Announce Type: new Abstract: The parity problem--deciding whether the number of ones in a binary vector is odd or even--remains challenging for standard neural networks due to linea

Test-time training was popularized during the ARC Prize 2024 competition, after being explored in particular by @MindsAI_Jack and team. To d…

researchfrancois-chollet--x

Test-time training was popularized during the ARC Prize 2024 competition, after being explored in particular by @MindsAI_Jack and team. To date, I believe ARC 1-2 are the only datasets where TTT stron

TGRHuman: Text-Guided Realistic 3D Human Generation via Diffusion Renderer

arXiv:2608.12175v1 Announce Type: new Abstract: Realistic 3D human generation plays a crucial role in many graphics applications. However, current methods still struggle to generate high-quality human

Thanks. The fact that it works so well for ARC is also a clue to the extent of generalization in these models. It was not at all obvious tha…

researchfrancois-chollet--x

Thanks. The fact that it works so well for ARC is also a clue to the extent of generalization in these models. It was not at all obvious that it would work originally because the model is never traine

The Advective Fisher-Rao Geometry of Deterministic Measure Transport

arXiv:2608.12111v1 Announce Type: cross Abstract: A novel advective Fisher-Rao metric is introduced for optimization tasks on paths of probability measures governed by the continuity equation. This me

The Edge-based Contiguous p-median Problem with Connections to Logistics Districting

arXiv:2608.11230v1 Announce Type: new Abstract: This paper introduces the edge-based contiguous p-median (ECpM) problem to partition the roads in a network into a given number of compact and contiguou

Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention

arXiv:2608.11427v1 Announce Type: new Abstract: Full attention exposes every token pair, whereas kernel attention compresses a sequence into a fixed-dimensional sketch. We show that this distinction b

Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp

arXiv:2608.11760v1 Announce Type: cross Abstract: We revisit the Sinkhorn-Knopp (SK) algorithm for the matrix scaling problem. Despite extensive literature on the global convergence of SK and its vari

Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training

arXiv:2604.07037v2 Announce Type: replace-cross Abstract: Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally d

Towards Model-based Run-time Cybersecurity: On Control-Flow Anomaly Detection, Attack Identification, and Hardware Monitoring

arXiv:2608.11802v1 Announce Type: cross Abstract: Methods to increase the resilience of systems to cyber-attacks become increasingly important. Control-flow monitoring provides a principled basis to e

Towards Tighter Convex Relaxation of Mixed-Integer Programs: Leveraging Logic Network Flow for Task and Motion Planning

arXiv:2509.24235v2 Announce Type: replace Abstract: This paper proposes an optimization-based task and motion planning framework, named 'Logic Network Flow,' that integrates temporal logic specificati

researcharxiv-cs-ro

Towards Truly Unsupervised Evaluation of Feature Selection

arXiv:2608.12057v1 Announce Type: new Abstract: Feature selection is one of the most important and fundamental tasks in data mining, tackled by a family of methods with an established set of evaluatio

TradingMoE: Routing the Right Experts in Evolving Markets

arXiv:2608.11785v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predicti

Two-Stage Deformable-Convolutional Inverse Design of Nanophotonic Absorbers from Optical Spectra

arXiv:2608.11860v1 Announce Type: cross Abstract: Data-driven inverse design enables efficient generation of nanophotonic structures with prescribed optical responses, but spectrum-to-geometry mapping