Knowledge catalogue
arXiv:2608.07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive. Existing trai
arXiv:2608.07468v1 Announce Type: new Abstract: World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods requir
arXiv:2608.07106v1 Announce Type: new Abstract: Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the
arXiv:2608.06467v1 Announce Type: new Abstract: Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across
arXiv:2608.07398v1 Announce Type: cross Abstract: Production planning in the manufacturing industry often relies on the use of optimization models, but defining an appropriate objective function can b
arXiv:2505.16170v4 Announce Type: replace Abstract: We study the internal mechanisms that govern when LLMs choose to retract wrong answers, i.e., spontaneously and immediately acknowledge errors in th
arXiv:2608.07261v1 Announce Type: new Abstract: Large language models (LLMs) can solve complex multi-hop problems yet exhibit puzzling failures on simple two-hop queries: although a model may correctl
arXiv:2608.07033v1 Announce Type: new Abstract: This work investigates whether Electroencephalograph (EEG) foundation models (EFMs) can be made faster and locally deployable without sacrificing accura
Hi folks, I hate slop as much as you do, so instead of starting with 'The Problem', I'll just cut to the chase: I just published Lophius, which is the culmination of more than two years of fighting wi
Basically what the title says. For me, it would always crash and burn trying to use tensor split. Apparently, there's some bug where GPU memory gets corrupted with the default microbatch (512) or high
Build a 100% offline fast Retrieval Augmented Generation (RAG) system that runs without an internet connection, without cloud APIs, without OpenAI/Ollama Published a video where you can build a fully
arXiv:2608.06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to extit{syntactic structure}. We introduce extbf{
arXiv:2608.06023v1 Announce Type: new Abstract: To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of p
arXiv:2603.14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior duri
arXiv:2608.06216v1 Announce Type: cross Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g.,
arXiv:2608.05848v1 Announce Type: new Abstract: In K-12 educational scenarios, handwritten Chinese text recognition should not only transcribe student writing, but also detect faked characters. Howeve
arXiv:2608.06227v1 Announce Type: cross Abstract: Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when
arXiv:2608.05237v1 Announce Type: cross Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the curren
In the era of base LLM scaling (2022-2024), I believed the LLM line of research would reach a capability plateau (as later seen with base LLMs). In late 2024, after the o3 test-time compute demo, I ch
arXiv:2608.05739v1 Announce Type: new Abstract: Mobile image denoising requires both good restoration quality and low computational cost. In addition, it's annoying to collect large-scale LQ-GT clean
📝 Introduction We present Wan-Animate-2, a novel end-to-end character animation framework that directly consumes driving videos in a redesigned Diffusion Transformer, which achieves high-fidelity moti
Following up on yesterday's post about running everyone's faves on 2 x 16gb cards while maximizing performance and KV. Previous post data used abandoned Cu130 VLLM image. Stats here are done on cu129-
Among proponents of neurosymbolic architectures, there had been some debate over the years about whether the outer level would be symbolic (i.e. a harness that calls neural models) or whether the oute
arXiv:2608.04525v1 Announce Type: new Abstract: Scene text image super-resolution (STISR) aims to recover visually plausible appearance while preserving character semantics from degraded inputs. Exist
arXiv:2608.04996v1 Announce Type: new Abstract: World Action Models (WAMs) learn action-relevant representations by predicting how the observed world will evolve. Most existing WAMs define this future
arXiv:2508.00285v2 Announce Type: replace Abstract: Objective: Large Language Models (LLMs) have demonstrated strong capabilities in medical text understanding and generation. However, their trustwort
arXiv:2608.04050v1 Announce Type: cross Abstract: Wi-Fi networks are moving beyond random channel access toward tightly coordinated operation across access points (APs), a shift reflected in Wi-Fi 8's
Fortunately AI agents don't just cyberattack us. They also use us more than ever for what we're actually built for: the storage and collaboration layer for AI 😅 New record: almost 4 PB of private & pu
arXiv:2608.04612v1 Announce Type: new Abstract: We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clam
arXiv:2608.04610v1 Announce Type: new Abstract: 3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated obser
It was the verification problem all along, while the masses were distracted by the alignment problem. Recursive self improvement? How does the observer observe itself and know that it changed for the
arXiv:2608.04365v1 Announce Type: new Abstract: Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning
arXiv:2608.04939v1 Announce Type: new Abstract: Social media videos often communicate meanings that go beyond their visible actions, captions, or speech. A mundane clip may become humorous, ironic, or
arXiv:2608.05097v1 Announce Type: new Abstract: Reasoning about necessity and possibility depends on assumptions about accessibility between worlds and about which objects exist at each one. The same
arXiv:2603.14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of pretrained Di
Taalas buried the lede for the amazing demo of their first tape out. 15k tokens per second with a llama 8b model, ability to scale that up etched onto silicon As models satisfice etching makes sense,
arXiv:2608.03475v1 Announce Type: cross Abstract: Multimodal intent recognition combines linguistic, acoustic, and visual evidence, but individual modalities may be noisy, missing, semantically confli
arXiv:2608.03154v1 Announce Type: new Abstract: Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and
arXiv:2608.03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based
arXiv:2608.03464v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in chart understanding, generation, and editing, but their ability to annotate e
DeepSeek V4 Flash 0731 is ready to fine-tune on Fireworks. Run SFT, DPO, and RL training jobs on the Dedicated Training API. SFT and DPO from the managed UI. Built for coding agents and high-volume pr
arXiv:2608.01755v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize chain-of-thought (CoT) supervision to enhance the reason
arXiv:2608.03681v1 Announce Type: new Abstract: Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifying
arXiv:2608.03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typic
arXiv:2608.03036v1 Announce Type: cross Abstract: Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Se
arXiv:2608.03708v1 Announce Type: new Abstract: Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single
arXiv:2608.02845v1 Announce Type: new Abstract: Tabular model performance degrades when feature distributions change over time or the relationship between features and outcome variables change over ti
arXiv:2608.03041v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) approaches for flexible job shop scheduling (FJSP) heavily rely on attention-centric architectures to achieve state-
arXiv:2511.21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies. We stu
arXiv:2608.02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researche
arXiv:2608.03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but
We run a local model instance in our company that the dev we hired built for us. We're a trade business and we want to further use our on hand hardware for it. The specs given we have is a 5090 gpu wi
arXiv:2608.03918v1 Announce Type: cross Abstract: Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence.
arXiv:2608.00434v1 Announce Type: new Abstract: Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training th
arXiv:2608.00361v1 Announce Type: new Abstract: Optical microscopy of particle and fiber dispersions involves interpreting subtle visual cues influenced by specimen morphology, chemical composition, m
Surging AI demands are driving the need for massive datasets and context windows that burst past the confines of system memory. But rising needs aren’t met by simply adding more storage capacity. What
arXiv:2608.02016v1 Announce Type: new Abstract: Sparse voxel grids preserve the spatial structure needed for detailed 3D reconstruction, but their memory still grows rapidly with resolution as active
arXiv:2608.00714v1 Announce Type: new Abstract: Recent advances in large vision-language models (LVLMs) have enabled long-video understanding and analysis. However, processing the large number of fram
arXiv:2608.01821v1 Announce Type: new Abstract: Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual c
Just wanted to share my agentic coding benchmark run of DSv4F 0731 at both High and Low reasoning efforts (not Max)... I ran a 109-question subset of Aider Polyglot (the JS/C++/Python languages), base