Knowledge catalogue
arXiv:2508.05170v3 Announce Type: replace-cross Abstract: In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects op
arXiv:2605.03269v1 Announce Type: cross Abstract: While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intellig
arXiv:2605.03821v1 Announce Type: new Abstract: Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly ali
arXiv:2603.15969v2 Announce Type: replace Abstract: The Romansh language has several regional varieties, called idioms, which sometimes have limited mutual intelligibility. Despite this linguistic div
arXiv:2605.03678v1 Announce Type: new Abstract: Reliable localization in GPS-denied, visually degraded environments is critical for autonomous UAV opera- tions. This paper presents a systematic compar
arXiv:2605.03720v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mat
arXiv:2605.03706v1 Announce Type: new Abstract: Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large l
arXiv:2601.04809v5 Announce Type: replace Abstract: Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on
arXiv:2507.00994v4 Announce Type: replace Abstract: Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked
arXiv:2601.04025v2 Announce Type: replace Abstract: Advances in large language models (LLMs) enable many new innovations in education. However, evaluating the effectiveness of new technology requires
arXiv:2604.04328v3 Announce Type: replace-cross Abstract: The evaluation of general-purpose artificial agents, particularly those based on LLMs, presents a significant challenge due to the non-transit
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this sparsity into practical
arXiv:2605.02904v1 Announce Type: new Abstract: We present StateSMix, a fully self-contained lossless compressor that couples an online-trained Mamba-style State Space Model (SSM) with sparse n-gram c
arXiv:2605.03907v1 Announce Type: new Abstract: Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform
arXiv:2605.02545v1 Announce Type: new Abstract: Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strateg
arXiv:2605.03849v1 Announce Type: new Abstract: Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching
arXiv:2605.02973v1 Announce Type: new Abstract: Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusio
arXiv:2605.03534v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds answers in retrieved passages, but retrieval is not verification: a passage can be topical and still fail t
arXiv:2605.03221v1 Announce Type: new Abstract: Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically u
arXiv:2605.01750v1 Announce Type: cross Abstract: Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose. While static grounding maps lan
arXiv:2605.03909v1 Announce Type: cross Abstract: Robotic laser profiling is widely used for dimensional verification and surface inspection, yet measurement fidelity is often dominated by sensor conf
arXiv:2605.02024v1 Announce Type: new Abstract: In Dung-style abstract argumentation, various semantics capture notions of acceptability of arguments. The admissibility semantics capture the notion th
arXiv:2605.00914v1 Announce Type: cross Abstract: Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review
The last sentence in this abstract is really important, in a way that professional programmers will immediately recognize: the models favored big single files rather than breaking things into modules.
arXiv:2605.03258v1 Announce Type: cross Abstract: Large language models often fail at simple counting tasks, even when the items to count are explicitly present in the prompt. We investigate whether t
arXiv:2604.25000v2 Announce Type: replace Abstract: Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems w
arXiv:2605.03348v1 Announce Type: new Abstract: We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of en
arXiv:2605.01102v1 Announce Type: new Abstract: Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a
arXiv:2605.03789v1 Announce Type: cross Abstract: We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed res
arXiv:2605.03953v1 Announce Type: cross Abstract: Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low
arXiv:2605.01970v2 Announce Type: cross Abstract: Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characte
arXiv:2605.03950v1 Announce Type: new Abstract: Although recent LMMs have become much stronger at visual perception, they remain unreliable on problems that require multi-step reasoning over visual ev
arXiv:2605.03677v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models
arXiv:2605.03716v1 Announce Type: new Abstract: Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing met
arXiv:2605.02591v1 Announce Type: new Abstract: The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions, yet existing approaches often struggle to bala
arXiv:2605.03752v1 Announce Type: new Abstract: Multi Armed Bandit (MAB) algorithms are a cornerstone of reinforcement learning and have been studied both theoretically and numerically. One of the mos
arXiv:2605.03096v1 Announce Type: cross Abstract: In classification tasks, models may rely on confounding variables to achieve strong in-distribution performance, capturing spurious features that fail
arXiv:2605.02463v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, t
arXiv:2605.03314v1 Announce Type: new Abstract: In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling
arXiv:2605.02920v1 Announce Type: cross Abstract: Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode.
arXiv:2605.02777v1 Announce Type: new Abstract: Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a s
arXiv:2511.04685v2 Announce Type: replace Abstract: In this work, we present the solution approach for the Integrated Healthcare Timetabling Competition 2024 submitted by Team Twente, which ultimately
arXiv:2605.00903v1 Announce Type: new Abstract: Agriculture is a key sector of the economies of developing countries. It serves as a primary source of income and employment for rural populations. Howe
arXiv:2605.01336v1 Announce Type: new Abstract: News outlets shape public opinion at a scale that makes automated detection of political bias and factuality essential. However, the field still lacks u
arXiv:2605.02035v1 Announce Type: new Abstract: Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous e
arXiv:2605.01034v1 Announce Type: new Abstract: As large language models grow increasingly capable, concerns about their safe deployment have intensified. While numerous alignment strategies aim to re
arXiv:2605.01657v1 Announce Type: new Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic in
arXiv:2605.01345v1 Announce Type: new Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevita
arXiv:2605.02849v1 Announce Type: new Abstract: Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires contr
arXiv:2605.01968v1 Announce Type: new Abstract: Offline reinforcement learning (RL) can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the crit
arXiv:2602.00074v2 Announce Type: replace-cross Abstract: While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with 'workflow friction' from manual da
arXiv:2511.21678v2 Announce Type: replace-cross Abstract: MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the sam
Eight months after closing a 350 million funding round, Sierra Technologies Inc. today announced that it has raised an additional 950 million at a 15 billion valuation. Alphabet Inc.’s GV venture capi
arXiv:2512.09169v2 Announce Type: replace-cross Abstract: We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within
arXiv:2605.00937v1 Announce Type: cross Abstract: We propose an arbitrary Lagrangian-Eulerian (ALE)-consistent machine learning framework for long-term fluid-structure interaction (FSI) prediction on
arXiv:2605.01544v1 Announce Type: new Abstract: Imitation learning (IL) has seen remarkable progress, yet field deployment of IL-powered robots remains hindered by the challenge of out-of-distribution
arXiv:2605.00855v1 Announce Type: cross Abstract: We study the deterministic global optimization of trained Gaussian process posterior mean functions over hyperrectangular domains. Although the poster
arXiv:2605.02667v1 Announce Type: cross Abstract: Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone t
arXiv:2605.02320v1 Announce Type: cross Abstract: Proximal Policy Optimization (PPO) dominates deep RL but faces a fundamental dilemma. Its 'hard clipping' mechanism discards valuable gradient informa
arXiv:2601.00237v2 Announce Type: replace Abstract: This paper addresses the critical bottleneck of infrared (IR) data scarcity in Printed Circuit Board (PCB) defect detection by proposing a cross-mod