Qwen 3.8 27b (Q4KM) oneshot a Super Mario clone
I am absolutely blown away. Yes my setup is crap but the fact that it managed to do this in a single take is unbelievable (and I'm a developer). Hardware used: - Windows PC with 4070ti (12GB VRAM, 32G
Knowledge catalogue
I am absolutely blown away. Yes my setup is crap but the fact that it managed to do this in a single take is unbelievable (and I'm a developer). Hardware used: - Windows PC with 4070ti (12GB VRAM, 32G
if you are on Qwen Flash Next make sure to update your build often https://preview.redd.it/zoq3j9gnjvmh1.jpg?width=900&format=pjpg&auto=webp&s=bb21bc405696df94fd5ce38c22f4ca6dc596135f merged already (
arXiv:2608.30896v1 Announce Type: new Abstract: Automotive mmWave radar can develop vibration, antenna misalignment, radome blockage, and receive-channel degradation that corrupt the signal before per
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later priv
arXiv:2608.30156v1 Announce Type: new Abstract: Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise
arXiv:2608.30270v1 Announce Type: new Abstract: Indirect speech acts (ISAs) require pragmatic reasoning over context, as directive intent can- not be inferred from surface form alone. Prior text-based
arXiv:2608.30609v1 Announce Type: cross Abstract: Large language models are increasingly capable in general, but their utility can remain modest in niche or understudied areas. One approach to address
arXiv:2601.13206v2 Announce Type: replace Abstract: Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiat
arXiv:2608.30617v1 Announce Type: new Abstract: Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. Howeve
arXiv:2608.30820v1 Announce Type: new Abstract: Occlusion boundaries (OBs) are pixel-level image boundaries corresponding to surface visibility discontinuities caused by occlusion. Through precise bou
arXiv:2608.30627v1 Announce Type: new Abstract: As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token predi
arXiv:2608.28607v1 Announce Type: new Abstract: Pharmaceutical sponsors developing a drug for both the United States and the European Union must reconcile guidance issued independently by the FDA and
arXiv:2505.03654v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models have shown strong performance across multimodal tasks, and recent personalized MLLMs can recognize user-speci
arXiv:2608.29899v1 Announce Type: cross Abstract: Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models
Remember that every news announcement from an AI lab is about $20,000 in product and marketing insights for free. When they provide a few bullets of what a new model can do, it’s based off of the prev
arXiv:2608.28963v1 Announce Type: cross Abstract: The number of knowledge graph databases has increased significantly with the proliferation of knowledge graph technologies. Knowledge graphs enable th
arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengin
arXiv:2608.28639v1 Announce Type: new Abstract: Formal theorem proving with large language models remains challenging due to the difficulty of navigating large proof search spaces efficiently. Existin
arXiv:2603.10807v2 Announce Type: replace-cross Abstract: Existing LLM safety evaluations rely on binary attack-success rates and domain-agnostic taxonomies, leaving regulated Banking, Financial Servi
arXiv:2608.28718v1 Announce Type: cross Abstract: Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) be
arXiv:2608.29983v1 Announce Type: new Abstract: Broad Learning System (BLS) offers an efficient alternative to deep architectures by enabling fast learning through randomized feature mapping and close
arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assump
arXiv:2608.29058v1 Announce Type: new Abstract: Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention head
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,
arXiv:2503.00030v3 Announce Type: replace-cross Abstract: Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference
arXiv:2608.27906v2 Announce Type: replace Abstract: Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unli
arXiv:2608.31100v1 Announce Type: new Abstract: Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent bench
arXiv:2608.29098v1 Announce Type: new Abstract: Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, howeve
arXiv:2608.29770v1 Announce Type: new Abstract: Planners on graphs of convex sets return trajectories that are collision-free by construction, provided the convex regions are collision-free. The regio
arXiv:2608.29419v1 Announce Type: cross Abstract: Deep learning architectures are increasingly proposed for patient trajectory modeling in electronic health records (EHRs), yet their advantage over si
arXiv:2603.08814v2 Announce Type: replace-cross Abstract: Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; ye
arXiv:2512.03244v2 Announce Type: replace-cross Abstract: Training process reward models (PRMs) requires step-level correctness labels, obtained either through expensive human annotation or by relying
arXiv:2608.30517v1 Announce Type: new Abstract: Benchmark saturation and data contamination increasingly obscure genuine scientific reasoning in frontier LLMs. We introduce extsc{ScienceArena}, an oly
arXiv:2608.28715v1 Announce Type: cross Abstract: Ultrasound-guided interventions can require localization of an untracked 2D frame within a 3D anatomical reference. Rigid slice-to-volume registration
arXiv:2608.29953v1 Announce Type: new Abstract: Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchW
seems like it I hadn’t realized it until now, but could Microduck actually be the biggest launch of a new consumer robot ever? 10,500 robots ordered and $4.54M in sales in just 4 days. It’s surprising
arXiv:2608.30714v1 Announce Type: new Abstract: Verifying image authenticity is increasingly difficult, posing serious risks across journalism, law enforcement, and political domains. Most existing fo
arXiv:2608.30916v1 Announce Type: new Abstract: Agent evaluations often use one benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selec
arXiv:2608.30070v1 Announce Type: new Abstract: Sparse representations are often expected to make models smaller and also reduce inference cost. For Fourier Neural Operators (FNOs), these objectives a
arXiv:2608.29070v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in prin
arXiv:2608.28978v1 Announce Type: new Abstract: Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption tha
arXiv:2608.28638v1 Announce Type: new Abstract: Agent skills are portable packages of instructions and resources an agent consults at deployment. Self-evolving them fails in two ways today. First, ski
arXiv:2608.28647v1 Announce Type: new Abstract: Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before ad
arXiv:2608.30456v1 Announce Type: new Abstract: We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the sam
arXiv:2608.28911v1 Announce Type: cross Abstract: The key-value (KV) cache is the dominant memory bottleneck of long-context large language model (LLM) inference, growing linearly with context length.
arXiv:2608.30451v1 Announce Type: new Abstract: Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect tempor
arXiv:2512.18128v4 Announce Type: replace Abstract: High-resolution mapping of canopy height is essential for forest management and biodiversity monitoring. Although recent studies have led to the adv
arXiv:2512.15052v4 Announce Type: replace-cross Abstract: Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understandin
arXiv:2608.29270v1 Announce Type: cross Abstract: Autoformalization translates informal mathematical theorems into code for proof assistants such as Lean. A central challenge is that current evaluatio
arXiv:2509.22100v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved remarkable success across a range of learning tasks. However, scaling GNNs to large graphs remains a sign
arXiv:2608.31157v1 Announce Type: new Abstract: Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture P
arXiv:2608.29481v1 Announce Type: new Abstract: Pediatric serious illness communication (SIC) is critically important, yet scalable communication training for clinicians remains limited. Compared with
arXiv:2608.24888v2 Announce Type: replace Abstract: Agents that act on a user's behalf must plan differently for different users, and increasingly do so from some structured representation of user con
arXiv:2608.30703v1 Announce Type: cross Abstract: Runtime guardrails are essential for reliable large language model (LLM) deployment, yet existing approaches typically rely on independent, external m
arXiv:2508.09115v5 Announce Type: replace Abstract: Low-resource languages such as Sinhala are often overlooked by open-source Large Language Models (LLMs). In this research, we extend an existing mul
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal,
arXiv:2608.29841v1 Announce Type: new Abstract: Generating formally verified programs from natural language remains challenging: existing approaches either produce code in a single pass without recour
arXiv:2605.05726v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical
arXiv:2608.29921v1 Announce Type: cross Abstract: The output of a Language Model can be tampered with while the model is writing it. A simple test can thus be constructed by evaluating the model's per
arXiv:2602.11166v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed