Knowledge catalogue
arXiv:2605.27899v1 Announce Type: new Abstract: Structured skill prompts improve exploration in long-horizon agentic reinforcement learning (RL). Skill-augmented RL methods retain external skills at i
arXiv:2605.28153v1 Announce Type: cross Abstract: Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging
Spectacular work by @ClementDelangue and the team at @huggingface! The HF science team just made async RL weight sync ~100x cheaper on bandwidth, and you don't need a shared cluster anymore. The probl
arXiv:2605.28490v1 Announce Type: cross Abstract: 3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together w
arXiv:2605.28711v1 Announce Type: new Abstract: The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between dist
arXiv:2505.18647v3 Announce Type: replace-cross Abstract: Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and
arXiv:2605.27927v1 Announce Type: new Abstract: Image inputs enable Large Vision Language Models (LVLMs) to perceive fine-grained visual information, but also introduce a pixel-level attack surface th
arXiv:2505.13820v5 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-sty
arXiv:2605.27790v1 Announce Type: new Abstract: Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded dur
arXiv:2605.28372v1 Announce Type: new Abstract: Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex an
arXiv:2605.28020v1 Announce Type: new Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The
arXiv:2605.28699v1 Announce Type: new Abstract: Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain d
arXiv:2605.27659v1 Announce Type: cross Abstract: Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicle
arXiv:2605.27676v1 Announce Type: cross Abstract: Fine-tuning a pretrained language model on a curated dataset can produce spurious correlations between the fine-tuning task and unintended latent fact
arXiv:2605.27721v1 Announce Type: cross Abstract: Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mi
Ollama v0.30.0-rc29 is a pre-release version that changes the architecture to directly support llama.cpp instead of building on top of GGML, and adds compatibility with the GGUF file format. MLX is us
arXiv:2605.28527v1 Announce Type: new Abstract: Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Thei
arXiv:2605.28181v1 Announce Type: new Abstract: Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inferenc
arXiv:2605.27997v1 Announce Type: cross Abstract: Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-leve
arXiv:2503.18893v2 Announce Type: replace Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent st
arXiv:2605.27580v1 Announce Type: new Abstract: A central puzzle for the behavioural sciences and for human-facing artificial intelligence is the persistence of within-person variability. The same ind
arXiv:2512.08371v4 Announce Type: replace Abstract: Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtai
arXiv:2605.26763v1 Announce Type: cross Abstract: The Maximal Covering Location-Interdiction Problem (MCLIP) is a classic bi-level optimization problem, which is fundamental to resilient infrastructur
Latent Space reports on emerging AI infrastructure companies achieving unicorn status, specifically highlighting Fireworks and Baseten as new decacorns (companies valued at $10+ billion), with OpenRou
arXiv:2511.16870v3 Announce Type: replace Abstract: Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encode
arXiv:2605.26178v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. Howeve
The search results do not contain specific details about release b9354. Based on the context from the llama.cpp project, b9354 is a build release of llama.cpp, a C/C++ implementation for running large
arXiv:2505.13775v4 Announce Type: replace-cross Abstract: Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the proc
arXiv:2605.26627v1 Announce Type: cross Abstract: Deploying reinforcement learning in safety critical domains, from autonomous vehicles to medical decision support, is constrained by failures arising
arXiv:2605.27043v1 Announce Type: cross Abstract: Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the traini
arXiv:2605.27281v1 Announce Type: new Abstract: Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call
arXiv:2605.26192v1 Announce Type: cross Abstract: Protein structure generative models excel at predicting single protein static structures from sequence, but routinely fail to capture the correct conf
arXiv:2601.22519v2 Announce Type: replace-cross Abstract: Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alter
arXiv:2605.26449v1 Announce Type: cross Abstract: Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-f
arXiv:2605.26629v1 Announce Type: new Abstract: Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fail
arXiv:2510.07231v4 Announce Type: replace-cross Abstract: Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, e
arXiv:2605.26637v1 Announce Type: new Abstract: Most existing embodied intelligence methods formulate perception, reasoning, planning, and control within a unified parameterized policy. Yet these capa
arXiv:2601.09001v4 Announce Type: replace Abstract: Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improveme
arXiv:2605.27351v1 Announce Type: new Abstract: 3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generati
arXiv:2506.10225v2 Announce Type: replace-cross Abstract: Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of
arXiv:2503.20507v4 Announce Type: replace-cross Abstract: Modern high-performance computing (HPC) environments rely on hybrid storage systems (HSS) that combine multiple storage devices with diverse l
arXiv:2508.18444v2 Announce Type: replace-cross Abstract: With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with huma
arXiv:2605.26421v1 Announce Type: new Abstract: The rapid evolution of generative models has precipitated a proliferation of fabricated content, posing significant challenges to existing Synthetic Ima
arXiv:2605.27138v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific data from trained language models. In real-world deployments, unlearning requests often arri
arXiv:2605.26902v1 Announce Type: cross Abstract: Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansi
arXiv:2605.26307v1 Announce Type: cross Abstract: Software-Defined Networking (SDN) provides flexible and programmable network management; however, its centralized control architecture remains highly
arXiv:2605.27288v1 Announce Type: cross Abstract: Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behav
arXiv:2605.26636v1 Announce Type: cross Abstract: We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention
arXiv:2511.14993v3 Announce Type: replace-cross Abstract: This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis.
arXiv:2511.02360v4 Announce Type: replace-cross Abstract: Chain of Thought (CoT) reasoning enhances logical performance by decomposing complex tasks, yet its multimodal extension faces a trade-off. Th
arXiv:2605.26828v1 Announce Type: new Abstract: Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated
arXiv:2601.18987v5 Announce Type: replace-cross Abstract: Determining whether a program terminates is a central problem in computer science. Turing's Halting Problem established termination as undecid
arXiv:2605.27365v1 Announce Type: cross Abstract: Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into
arXiv:2605.26486v1 Announce Type: new Abstract: Despite advances in audio-driven video generation, achieving commercial-grade stability remains challenging. We present LongCat-Video-Avatar 1.5, an upg
arXiv:2605.27186v1 Announce Type: new Abstract: Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lo
arXiv:2605.27345v1 Announce Type: new Abstract: Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g.,
arXiv:2601.08267v3 Announce Type: replace Abstract: While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents
arXiv:2601.18904v2 Announce Type: replace-cross Abstract: Auditory Large Language Models (LLMs) have demonstrated strong performance across a wide range of speech and audio understanding tasks. Nevert
arXiv:2605.26444v1 Announce Type: new Abstract: Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection l