Knowledge catalogue
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, b
arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Exist
Small models, big real-world impact. Proud to see Qwen leading local inference in the State of Open Models. Enjoy the sunshine from Qwen.☀️ 😎 Appreciate your work! @huggingface The State of Open Model
arXiv:2608.12875v1 Announce Type: new Abstract: Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across
arXiv:2608.12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. O
arXiv:2608.13047v1 Announce Type: new Abstract: Driven by the availability of large-scale datasets, Human Pose Estimation (HPE) plays a critical role in numerous downstream tasks. However, mainstream
arXiv:2608.13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more
arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enfo
arXiv:2608.12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forc
arXiv:2608.11555v1 Announce Type: new Abstract: Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-
arXiv:2608.11650v1 Announce Type: cross Abstract: Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS s
arXiv:2608.11731v1 Announce Type: new Abstract: Contact-implicit trajectory optimization avoids prescribing contact sequences, but yields mathematical programs with complementarity constraints (MPCCs)
There's no training anywhere in this. I ported Doom's actual rendering algorithm into transformer weights using a compiler I wrote (torchwright) -- every weight computed, none learned. The prompt carr
Some people told me that the difference in richness and layout between Glimmer and Qwen wasn't clear to them. This example makes it super clear. I'm aware that comparing Glimmer 30B (a dense model) wi
arXiv:2509.16749v1 Announce Type: cross Abstract: LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to securi
arXiv:2601.12178v2 Announce Type: replace Abstract: We propose a federated learning framework for the calibration of parametric insurance indices under heterogeneous renewable energy production losses
arXiv:2608.11367v1 Announce Type: cross Abstract: Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage p
arXiv:2608.11396v1 Announce Type: cross Abstract: Extracting quantum information from a quantum state is a fundamental task of quantum computation, often requiring the estimation of many non-commuting
To my fellow crazies, the few. Those who dared wrestle with llama-70b, mistral-large, goliath, mistral8x22B, DeepSeekV2/3, wept when llama4 behemoth was announced, picked yourself up and are now wrest
Reducing Retrieval and Calls When a retrieval-augmented generation (RAG) agent runs, it often has to plan a search, check the evidence it gets back, and try again when that evidence falls short. Those
arXiv:2608.11977v1 Announce Type: new Abstract: Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, per
arXiv:2608.11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks wit
arXiv:2608.12127v1 Announce Type: new Abstract: Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is
arXiv:2606.09498v2 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Be
Stumbled across this new vision model, SenseNova-Vision. It's a 7B MoT model, Apache 2.0 license, which is cool. The main idea is it treats pretty much all computer vision stuff as just one generation
arXiv:2608.11236v1 Announce Type: cross Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue
arXiv:2608.11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure. It is therefore experiencing a surge of renewed engineering
arXiv:2608.12150v1 Announce Type: new Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the toke
arXiv:2608.10939v1 Announce Type: cross Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet
arXiv:2608.11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident pr
arXiv:2608.10030v1 Announce Type: new Abstract: As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these
arXiv:2608.10798v1 Announce Type: cross Abstract: Most image colorization systems operate in Lab space by predicting chroma (ab) while preserving an input-derived luminance channel (L). While effectiv
arXiv:2608.10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over
arXiv:2608.10345v1 Announce Type: new Abstract: Free-viewpoint 3D scene media is increasingly important for immersive applications, yet practical capture often suffers from severe view sparsity and mo
arXiv:2512.22525v2 Announce Type: replace Abstract: Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text
arXiv:2608.10503v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NL
arXiv:2608.10499v1 Announce Type: cross Abstract: Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences whi
arXiv:2608.10805v1 Announce Type: cross Abstract: Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive fie
arXiv:2608.10860v1 Announce Type: cross Abstract: World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction,
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed re
arXiv:2608.10426v1 Announce Type: new Abstract: Open-vocabulary remote sensing segmentation has recently emerged as a promising paradigm that enables pixel-level recognition of arbitrary categories sp
Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon SageMaker AI, with a RAG pipeline on pgvector an
arXiv:2608.10414v1 Announce Type: new Abstract: Large Language Models (LLMs) are typically evaluated on standard written Vietnamese, yet everyday communication frequently involves regional dialects th
arXiv:2608.09938v1 Announce Type: cross Abstract: Hyperelastic deformations are highly sensitive to domain geometry and boundary conditions, making generalization across both a critical capability for
arXiv:2608.10485v1 Announce Type: new Abstract: Multi-object tracking (MOT) onboard agile unmanned aerial vehicles (UAVs) remains challenging due to severe viewpoint jitter induced by camera ego-motio
arXiv:2608.10300v1 Announce Type: new Abstract: Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human re
arXiv:2608.11036v1 Announce Type: new Abstract: Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work prese
arXiv:2608.09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure be
arXiv:2608.10777v1 Announce Type: new Abstract: Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained re
arXiv:2608.10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve conti
arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c
Muse Glimmer 30B feels significantly more precise and reliable, it almost never drops the ball or breaks rules. However, its designs lack creative depth and richness. Qwen3.6 35B, on the other hand, i
arXiv:2608.10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspect
arXiv:2608.10513v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their
arXiv:2608.10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests l
arXiv:2509.21263v2 Announce Type: replace Abstract: Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer
arXiv:2608.10346v1 Announce Type: cross Abstract: Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations
arXiv:2608.11024v1 Announce Type: new Abstract: Attribute hallucination---where vision-language models (VLMs) correctly identify an object but mischaracterize its properties---is prevalent yet mechani
arXiv:2608.11095v1 Announce Type: new Abstract: Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wh