Knowledge catalogue
arXiv:2610.11228v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong potential for sequential recommendation through their ability to reason over complex m
arXiv:2610.11723v1 Announce Type: new Abstract: Multiplayer world models must ensure that independently controlled views remain consistent with one shared and persistent world. We introduce MultiWorld
It's been a long time coming, and I should have done this in the first place. But LumaBrowser is now open source. Since I first released it a year ago, it's had several thousand installs and an absolu
arXiv:2610.11605v1 Announce Type: cross Abstract: We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, train
arXiv:2610.11768v1 Announce Type: cross Abstract: Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about th
arXiv:2610.11631v1 Announce Type: cross Abstract: Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patt
arXiv:2610.11030v1 Announce Type: cross Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per ac
arXiv:2610.10655v1 Announce Type: cross Abstract: Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning
arXiv:2601.14994v2 Announce Type: replace-cross Abstract: Data contamination can invalidate benchmark evaluation when a model benefits from memorized evaluation content rather than genuine generalizat
arXiv:2610.12458v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that ex
arXiv:2610.11194v1 Announce Type: cross Abstract: Dexterous grasping is the foundational primitive in embodied AI, demanding massive data to train robust models. As real-world data collection is expen
arXiv:2610.10697v1 Announce Type: cross Abstract: Accurately simulating chaotic quantum many-body dynamics remains a major computational challenge for classical methods, due to the rapid buildup and s
arXiv:2610.12448v1 Announce Type: new Abstract: In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inferenc
arXiv:2603.07980v2 Announce Type: replace-cross Abstract: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks
arXiv:2610.11118v1 Announce Type: new Abstract: The next frontier for artificial general intelligence is tackling unresolved scientific problems, calling for benchmarks that assess progress beyond est
arXiv:2610.11294v1 Announce Type: new Abstract: Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot expr
arXiv:2610.11572v1 Announce Type: new Abstract: Adapting a pre-trained 3D Gaussian Splatting (3DGS) road scene to a new time of day requires learning appearance changes from a few anchor images while
Speculative decoding accelerates autoregressive generation in large language models. In each drafting stage, a lightweight draft model proposes tokens that the target model subsequently verifies. With
Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Be
arXiv:2610.11329v1 Announce Type: new Abstract: Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characte
arXiv:2610.11011v1 Announce Type: new Abstract: Gaussian splatting has emerged as a flexible representation for 3D reconstruction from posed images. However, existing methods are optimized primarily u
arXiv:2610.12081v1 Announce Type: new Abstract: Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026
arXiv:2610.11669v1 Announce Type: new Abstract: Holistic and semantics-aware co-speech gesture generation has advanced rapidly, yet evaluation remains behind: objective metrics do not consistently ref
arXiv:2610.10630v1 Announce Type: cross Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimens
arXiv:2609.32382v2 Announce Type: replace Abstract: We present our system for the PlurVA-LLM 2026 Shared Task Track-1, which focuses on pluralistic value alignment in the contexts of China, Indonesia,
arXiv:2610.11423v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by aligning its policy with a teacher model on trajectories generated by the student model itself. T
arXiv:2610.12137v1 Announce Type: cross Abstract: Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM), is a growing threat to model
arXiv:2610.12410v1 Announce Type: cross Abstract: LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target. However, while
arXiv:2512.16545v3 Announce Type: replace-cross Abstract: Cu NPs have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with
arXiv:2610.11460v1 Announce Type: cross Abstract: Prototypes in classification models are almost always vectors, and a vector has no readable form. This paper asks what happens when a prototype is an
arXiv:2610.12423v1 Announce Type: new Abstract: We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation mod
arXiv:2610.11261v1 Announce Type: cross Abstract: Variational quantum algorithms are often limited by barren plateaus: gradients vanish as circuit size and depth increase, making quantum neural networ
arXiv:2610.11134v1 Announce Type: new Abstract: Sparse attention reduces the cost of long-context attention, but existing kernels typically process queries independently, repeatedly loading and dequan
Referring to specifically Unsloth's UD_Q4_K_XL quant because that's going to be a question, and is relevant regardless. It's old now. It's not great at coding medium sized or even small-ish projects.
(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next
Qwen-Image-2.1-Turbo, create and edit images in just 8 denoising steps! Open weights now available! Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation archite
I wanted the uncensored Qwen3.8-27B (llmfan46's Heretic build, MTP head preserved) on my RTX 4080 with MTP on (because I've been testing TONS of configs, and realized that would be the one) And none o
arXiv:2610.11146v1 Announce Type: new Abstract: Cold-start credit scoring -- deploying models with scarce labeled data, weak features, or minimal capacity -- is a recurring problem in financial machin
arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context acro
ik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,
arXiv:2610.12007v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental
arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through
arXiv:2610.10845v1 Announce Type: cross Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every t
arXiv:2610.12249v1 Announce Type: cross Abstract: We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rat
arXiv:2610.12343v1 Announce Type: new Abstract: Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, p
arXiv:2610.11004v1 Announce Type: cross Abstract: Reconstructing spatially resolved plasma dynamics from few sensors is essential for diagnostics, reduced-order modelling and control, yet remains diff
arXiv:2610.10623v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation s
arXiv:2610.11287v1 Announce Type: cross Abstract: Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent dec
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to pra
arXiv:2610.10947v1 Announce Type: new Abstract: Reward hacking, where a model exploits an evaluation signal without completing the intended task, threatens the reliability of deployed language model s
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics,
arXiv:2610.11164v1 Announce Type: new Abstract: We release Ride-Hailing, a large-scale ride-hailing time series dataset synthesized from DiDi's marketplace data across 200 spatial areas. Ride-Hailing
arXiv:2610.12244v1 Announce Type: new Abstract: Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-for
arXiv:2610.11370v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolate
arXiv:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent
arXiv:2510.25257v2 Announce Type: replace Abstract: Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the p
I have rtx 4090 and 64 gb of ddr4 ram. This is enough to fit smaller quants of qfn, but I found them not great and switched back to qwen3.8. However, there are option that bother me a lot, buy huawei
arXiv:2610.12469v1 Announce Type: new Abstract: Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward
HauhauCS ships their uncensored Qwen3.8-27B as GGUF only. NInfer, a C++/CUDA wanted its own format. Now the same model that ran at 91.6 tok/s / 131K under llama.cpp does: 262K context (the model's ful
arXiv:2606.18096v2 Announce Type: replace-cross Abstract: Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-base