Knowledge catalogue
Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though! 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more ef
arXiv:2609.08602v1 Announce Type: new Abstract: Embodied planning increasingly relies on vision-language models (VLMs) to translate instructions and visual observations into executable action sequence
arXiv:2510.13852v3 Announce Type: replace-cross Abstract: Is an LLM telling you different facts than it's telling me? This paper introduces ConsistencyAI, an independent benchmark for measuring the fa
arXiv:2609.09370v1 Announce Type: new Abstract: Discrete black-box optimization is often addressed using approaches such as Sequential Model-Based Optimization (SMBO), which aims to improve sample eff
The downside of uncensoring a model is that it is known to potentially damage it, but CyberTiel is an even more capable software engineer than its censored TielCoder base, while allowing offensive sec
People keep on getting confused about this, so I looked at the safetensors on hf. To be precise, the main model about 551.566B parameters with 40 layers. The FFN experts total to 543.582B parameters,
arXiv:2609.10308v1 Announce Type: new Abstract: Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In th
arXiv:2602.13047v2 Announce Type: replace Abstract: Conversational speech reveals early signs of cognitive decline, including dementia and mild cognitive impairment (MCI). AI models show promise for s
arXiv:2609.09504v1 Announce Type: cross Abstract: We perform field-level likelihood-free inference of the matter density parameter Omega_m from simulated galaxy catalogs using machine learning models
arXiv:2609.08082v1 Announce Type: new Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to the
arXiv:2609.10144v1 Announce Type: cross Abstract: AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often rema
arXiv:2609.06188v1 Announce Type: new Abstract: Multimodal sentiment analysis and emotion recognition in conversations demand effective modeling of heterogeneous interactions across textual, acoustic,
arXiv:2503.08051v2 Announce Type: replace Abstract: In the era of generative AI, recommender systems are moving from precise prediction to trustworthy generation. Large language models (LLMs) support
Now available: ChatGPT for Financial Services. This is a tailored ChatGPT Work experience that combines built-in financial data with GPT-6 Astra’s reasoning. Teams can develop research, build financia
arXiv:2603.23114v2 Announce Type: replace Abstract: A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by in
Github Repo. Blog post. 💡 TL;DR (from the Github Readme) Spend less without making the agent do less useful work. SoL-Pi is a standalone extension for Pi that packages four reusable efficiency mechani
arXiv:2605.21694v2 Announce Type: replace-cross Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender
arXiv:2609.07549v2 Announce Type: replace Abstract: In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling,
arXiv:2609.10092v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate bec
arXiv:1907.06994v2 Announce Type: replace-cross Abstract: Mixtures of experts (MoE) are conditional mixture models in which both the mixing proportions and the component densities depend on the predic
arXiv:2609.06149v1 Announce Type: cross Abstract: Script-based malware remains a prevalent attack technique. These scripts often contain indicators of compromise (IOCs) that provide actionable threat
arXiv:2609.09349v1 Announce Type: new Abstract: Modern LLMs demonstrate impressive multilingual performance, yet standard benchmarks primarily reward selecting correct answers rather than evaluating g
arXiv:2609.09772v1 Announce Type: new Abstract: SymbolicLight V2 combines sparse event computation with continuous-state processing in a hybrid neuromorphic language architecture. Extending V1's spike
arXiv:2609.10303v1 Announce Type: new Abstract: Face recognition (FR) is a widely used modality for biometric authentication, but conventional models rely on visible-spectrum imagery and degrade when
arXiv:2609.05514v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents are increasingly used as proxies for human participants in social science research, yet it remains unclear wheth
arXiv:2609.06974v1 Announce Type: cross Abstract: Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. S
arXiv:2609.09949v1 Announce Type: cross Abstract: Real-world detectors must often interpret functional or ambiguous prompts, yet conventional models such as YOLO remain restricted to fixed class lists
arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a
arXiv:2609.10355v1 Announce Type: cross Abstract: Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained larg
arXiv:2609.08307v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balan
arXiv:2609.05435v1 Announce Type: new Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt
arXiv:2609.06161v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress, yet their massive storage and memory-bandwidth demands still hinder efficient deployment
arXiv:2609.07884v1 Announce Type: new Abstract: Recent work, such as Vision Banana, shows that lightweight instruction tuning can enable an image generator to achieve state-of-the-art performance acro
arXiv:2609.08725v1 Announce Type: new Abstract: In online A/B tests for real-time bidding (RTB), control and treatment models are typically trained on a shared serving log that includes data generated
arXiv:2609.05418v1 Announce Type: cross Abstract: Machine learning training workloads place unique demands on storage systems, yet most existing benchmarks focus on computational throughput rather tha
arXiv:2510.25323v4 Announce Type: replace Abstract: Normalizing flows are deep generative models that enable efficient likelihood estimation and sampling through invertible transformations. A key chal
arXiv:2609.08914v1 Announce Type: new Abstract: Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoi
arXiv:2609.07685v1 Announce Type: new Abstract: In real-world applications, pedestrian trajectory prediction models rely on inputs from detection and tracking systems. Prior trajectory prediction benc
arXiv:2609.06809v1 Announce Type: new Abstract: Modern stereo matching models fail when disparity crosses zero, with end-point error (EPE) rising by 4.6-37imes. Yet stereoscopic content, from cinema 3
Just a reminder for those out there itching to get into local llms - don't let FOMO or 'gear acquisition syndrom' take over. No matter the hobby, it's so easy to get stuck in a trap where we buy more
arXiv:2609.06055v1 Announce Type: new Abstract: Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavior
arXiv:2609.08896v1 Announce Type: cross Abstract: The rapid growth of multimodal data has intensified the need for question answering (QA) systems capable of reasoning across heterogeneous sources suc
arXiv:2609.06106v1 Announce Type: new Abstract: Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL met
arXiv:2609.07617v1 Announce Type: new Abstract: With the rise of live sports betting in recent years, tennis forecasting has expanded from pre-match prediction to models that update win probabilities
I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it. In the screenshot you can see the outcome of using the model with a
arXiv:2609.05694v1 Announce Type: new Abstract: Predicting olfactory qualities from molecular structure is an open problem in chemoinformatics. Although linear models can link molecular features to od
arXiv:2609.06557v1 Announce Type: new Abstract: Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires stick
arXiv:2609.08300v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural halluc
A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Region inference, agents that run for up to
If they truly believe the risk is that high, and I think they do, then we need 100x more research and understanding of it. That requires them to openly share their models, datasets, training code, and
arXiv:2609.06649v1 Announce Type: new Abstract: Reward hacking during reinforcement learning from verifiable rewards (RLVR) can induce reward seeking and broad misalignment in language models. Studyin
arXiv:2609.06018v1 Announce Type: new Abstract: Ideal point estimation is widely used to analyze and visualize political data. However, selecting the corresponding spatial model involves various trade
arXiv:2512.04821v4 Announce Type: replace Abstract: Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and
arXiv:2609.09009v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models (DDPMs) generate samples by starting from noise and repeatedly denoising while keeping each update close to the
arXiv:2609.05885v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has become the standard for parameter-efficient fine-tuning of large language models. Most LoRA variants follow a uniform-LR
arXiv:2508.11431v3 Announce Type: replace Abstract: An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally pres
arXiv:2602.09740v3 Announce Type: replace Abstract: Connected and Autonomous Vehicles (CAVs), which is critical for achieving Level-5 autonomous driving. Safe and reliable CAV navigation depends on ro
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inference
arXiv:2609.06473v1 Announce Type: new Abstract: Inference-time activation steering enables behavioral control of large language models without parameter modification, while post-training quantization
Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app