Knowledge catalogue
arXiv:2512.11470v2 Announce Type: replace-cross Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ funda
arXiv:2605.09212v1 Announce Type: new Abstract: Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, all
arXiv:2605.06241v2 Announce Type: replace Abstract: Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not
arXiv:2502.06818v3 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS). In vanilla CLIP, patch-wise image rep
arXiv:2605.08217v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more histo
arXiv:2602.11824v2 Announce Type: replace Abstract: Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visu
arXiv:2605.08311v1 Announce Type: cross Abstract: Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with
arXiv:2603.05066v2 Announce Type: replace Abstract: Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their abilit
arXiv:2605.08703v1 Announce Type: new Abstract: Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-sc
arXiv:2605.09196v1 Announce Type: cross Abstract: Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizon
arXiv:2603.14694v2 Announce Type: replace-cross Abstract: Rapid structural damage assessment from remote sensing imagery is essential for timely disaster response. Within human-machine systems (HMS) f
arXiv:2605.09076v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions c
arXiv:2605.08616v1 Announce Type: new Abstract: Collaborative machine learning (CML) enables multiple clients to train a global model jointly in a data-distributed setting. To address data privacy and
arXiv:2511.21600v2 Announce Type: replace-cross Abstract: The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and pu
arXiv:2605.10057v1 Announce Type: new Abstract: Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, a
arXiv:2605.10899v1 Announce Type: new Abstract: Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyo
arXiv:2605.09730v1 Announce Type: new Abstract: Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structur
arXiv:2510.03648v2 Announce Type: replace Abstract: Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments.
arXiv:2605.09417v1 Announce Type: new Abstract: Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent i
arXiv:2603.27977v2 Announce Type: replace Abstract: Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard
arXiv:2602.00327v2 Announce Type: replace Abstract: We explore the use of large language models (LLMs) for next-utterance anticipation in human dialogue. Despite recent advances in LLMs demonstrating
arXiv:2605.10285v1 Announce Type: cross Abstract: We present a theoretically grounded Gaussian process framework that leverages neural feature maps to construct expressive kernels. We show that the le
arXiv:2603.16593v2 Announce Type: replace Abstract: Inspection planning is concerned with computing the shortest robot path to inspect a given set of points of interest (POIs) using the robot's sensor
arXiv:2605.10327v1 Announce Type: cross Abstract: In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in qu
arXiv:2509.02372v3 Announce Type: replace-cross Abstract: Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training int
arXiv:2605.09038v1 Announce Type: new Abstract: Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especia
arXiv:2605.08519v1 Announce Type: new Abstract: Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for app
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chai
arXiv:2512.19219v2 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterog
arXiv:2605.08936v1 Announce Type: new Abstract: Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe r
arXiv:2605.08874v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation requires adapting image-level vision-language models such as CLIP to dense pixel-level prediction, which is challe
arXiv:2605.08680v1 Announce Type: cross Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix
arXiv:2605.09284v1 Announce Type: cross Abstract: Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine m
arXiv:2605.09746v1 Announce Type: cross Abstract: Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic i
arXiv:2605.10913v1 Announce Type: new Abstract: We introduce Shepherd, a functional programming model that formalizes meta-agent operations on target agents as functions, with core operations mechaniz
arXiv:2605.08784v1 Announce Type: new Abstract: Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise
arXiv:2605.08809v1 Announce Type: cross Abstract: Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddin
arXiv:2601.19914v2 Announce Type: replace-cross Abstract: Synthetic data has proven itself to be a valuable resource for tuning smaller, cost-effective language models to handle the complexities of mu
arXiv:2605.10498v1 Announce Type: cross Abstract: Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority c
arXiv:2502.11537v4 Announce Type: replace-cross Abstract: World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements
arXiv:2605.09423v1 Announce Type: new Abstract: LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interac
arXiv:2605.09070v1 Announce Type: cross Abstract: Many jailbreak attack research papers report attack success rates for a limited number of parameter settings, even though there are many combinations
arXiv:2605.09343v1 Announce Type: new Abstract: Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, or
arXiv:2605.09359v1 Announce Type: cross Abstract: Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skill
arXiv:2605.10114v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-cen
arXiv:2605.10831v1 Announce Type: cross Abstract: Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information
arXiv:2605.08738v1 Announce Type: cross Abstract: Structured pruning and knowledge distillation (KD) are typical techniques for compressing large language models, but it remains unclear how they shoul
arXiv:2605.10453v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model
arXiv:2601.22131v2 Announce Type: replace Abstract: Multi-objective optimization aims to solve problems with competing objectives. Evaluating such problems is often slow or expensive, limiting the bud
arXiv:2602.09317v2 Announce Type: replace-cross Abstract: Neural networks are increasingly used as fast surrogate models across various domains, but unconstrained predictions can violate physical, ope
arXiv:2601.11042v2 Announce Type: replace-cross Abstract: Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for para
arXiv:2508.08441v3 Announce Type: replace-cross Abstract: Automated molecular structure elucidation remains challenging, as existing approaches often depend on pre-compiled databases or restrict thems
arXiv:2605.08151v1 Announce Type: cross Abstract: LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models recei
arXiv:2508.14685v4 Announce Type: replace Abstract: While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We anal
arXiv:2605.09989v1 Announce Type: cross Abstract: Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from
arXiv:2604.01824v2 Announce Type: replace Abstract: We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for vide
arXiv:2502.00816v4 Announce Type: replace Abstract: We introduce Sundial, a family of native, flexible, and scalable time series foundation models. To predict the next-patch's distribution, we propose
arXiv:2602.21307v2 Announce Type: replace Abstract: What mathematical functions do neural network components learn? Symbolic distillation addresses this question by expressing neural network component
arXiv:2605.08835v1 Announce Type: new Abstract: The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low ta
arXiv:2605.09424v1 Announce Type: new Abstract: Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modality, r