Knowledge catalogue
Highlights: 👉 1M context for long-horizon agentic workflows 👉 Stronger agentic coding across frontend, repo-level, and terminal-based tasks 👉 Multimodal reasoning across text, image, and video inputs
Last week we announced DeepSeek-V4. Today we’re sharing a closer look at DeepSeek-V4 Pro on Together AI: 512K context, controllable reasoning modes, and cached-input pricing for long-context workloads
arXiv:2604.25040v1 Announce Type: cross Abstract: We propose a per-task leverage ratio for human-agent collaboration: human work displaced by an agent, divided by the human time required to specify th
arXiv:2604.25200v1 Announce Type: cross Abstract: Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical govern
arXiv:2511.16518v2 Announce Type: replace-cross Abstract: We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in
arXiv:2604.25325v1 Announce Type: cross Abstract: Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limit
arXiv:2604.25061v1 Announce Type: cross Abstract: Custom policy-learning pipelines in Spark fail for two coupled systems reasons: rowwise Python execution makes inference impractical, and driver-side
arXiv:2604.25902v1 Announce Type: new Abstract: Distributional and neural approaches to natural language semantics have been built almost exclusively on conventional linear algebra: vectors, matrices,
arXiv:2604.23581v1 Announce Type: cross Abstract: Agentic systems that chain reasoning, tool use, and synthesis into multi-step workflows are entering production, yet prevailing evaluation practices l
arXiv:2510.17381v2 Announce Type: replace Abstract: Detecting out-of-distribution (OOD) data is critical for machine learning, be it for safety reasons or to enable open-ended learning. However, beyon
arXiv:2604.23413v1 Announce Type: new Abstract: Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these external ser
arXiv:2604.22759v1 Announce Type: cross Abstract: In community question answering (cQA) platforms like Stack Overflow, related question retrieval is recognized as a fundamental task that allows users
arXiv:2604.24690v1 Announce Type: new Abstract: While Large Language Models (LLMs) have increasingly assisted in historical tasks such as text processing, their capacity for professional-level histori
arXiv:2410.13903v3 Announce Type: replace-cross Abstract: Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge
arXiv:2510.17687v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak att
arXiv:2604.23210v1 Announce Type: new Abstract: Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for
arXiv:2604.04733v2 Announce Type: replace-cross Abstract: Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concep
arXiv:2604.23829v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their ow
arXiv:2604.23057v1 Announce Type: new Abstract: We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four
arXiv:2604.23325v1 Announce Type: cross Abstract: Emotionally talking head video generation aims to generate expressive portrait videos with accurate lip synchronization and emotional facial expressio
arXiv:2604.23993v1 Announce Type: cross Abstract: Product mapping, the task of deciding whether two e-commerce listings refer to the same product, is a core problem for price monitoring and channel vi
arXiv:2505.17855v2 Announce Type: replace Abstract: Understanding sources of a model's uncertainty regarding its predictions is crucial for effective human-AI collaboration. Prior work proposes using
arXiv:2604.24572v1 Announce Type: new Abstract: The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), maintained by the Observational Health Data Sciences and Informatics (OHDSI
arXiv:2604.24062v1 Announce Type: new Abstract: Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and
arXiv:2604.24558v1 Announce Type: new Abstract: Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option r
I post-trained Qwen3-Coder to fix bugs using an actual debugger. The result: Solve rate: 70% → 89% Median turns to fix: 46 → 19 (-59%) Instead of just reading code or print-debugging, it: - reasons fr
arXiv:2604.23584v1 Announce Type: new Abstract: Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal
arXiv:2604.23446v1 Announce Type: new Abstract: Industrial maintenance environments increasingly rely on AI systems to assist operators in understanding asset behavior, diagnosing failures, and evalua
arXiv:2604.24376v1 Announce Type: new Abstract: Depression places substantial pressure on mental health services, and many people describe their experiences outside clinical settings in high-volume us
arXiv:2604.23950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant
arXiv:2604.23897v1 Announce Type: new Abstract: Markets are a promising way to coordinate AI agent activity for similar reasons to those used to justify markets more broadly. In order to effectively p
arXiv:2604.24178v1 Announce Type: cross Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives
arXiv:2604.23129v1 Announce Type: cross Abstract: Knowledge workers face increasing challenges in synthesizing information from multiple documents into structured conceptual understanding. This proces
arXiv:2604.23788v1 Announce Type: new Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangeme
Nvidia Corp. today launched a powerful reasoning artificial intelligence model that unifies text, vision and speech, capable of acting as the “brains” of faster, smarter agentic AI applications. Dubbe
arXiv:2604.23036v1 Announce Type: cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fra
arXiv:2604.23443v1 Announce Type: new Abstract: Stochastic sampling strategies are widely adopted in large language models (LLMs) to balance output coherence and diversity. These heuristics are often
arXiv:2604.24036v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains undere
arXiv:2604.24544v1 Announce Type: new Abstract: The increasing reliance on Large Language Models (LLMs) across diverse sectors highlights the need for robust domain-specific and language-specific eval
arXiv:2604.24562v1 Announce Type: new Abstract: Driving in compliance with traffic laws and regulations is a basic requirement for human drivers, yet autonomous vehicles (AVs) can violate these requir
arXiv:2502.03669v3 Announce Type: replace-cross Abstract: AI methods, such as generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, espe
arXiv:2510.08045v2 Announce Type: replace-cross Abstract: We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provi
arXiv:2512.10362v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) demonstrate impressive reasoning capabilities, but often fail to perceive fine-grained visual details
arXiv:2604.22256v1 Announce Type: cross Abstract: Goal recognition aims to infer an agent's goal from observations of its behaviour. In realistic settings, recognition can benefit from exploiting hier
arXiv:2602.11931v2 Announce Type: replace-cross Abstract: Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large la
arXiv:2604.22517v1 Announce Type: new Abstract: Evaluating LLM-generated business ideas is often harder to scale than generating them. Unlike standard NLP benchmarks, business idea evaluation relies o
arXiv:2604.22128v1 Announce Type: new Abstract: When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: i
arXiv:2604.22580v1 Announce Type: cross Abstract: As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network pre
arXiv:2604.21950v1 Announce Type: cross Abstract: Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask whether composing them int
@idarbek Having your backups on the same vendor as your production database puts you at risk of your vendor banning your account for some reason (like billing messups, or detected CSAM in user-uploade
arXiv:2604.22577v1 Announce Type: new Abstract: Autonomous agent systems such as OpenClaw introduce significant efficiency challenges due to long-context inputs and multi-turn reasoning. This results
arXiv:2601.12979v3 Announce Type: replace Abstract: The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Three reasons why DeepSeek’s new model matters On Friday, Chin
The people building the most powerful technology in history cannot tell you what is happening inside their own systems. This is insane. We started the Torchbearer Community for exactly this reason. Re
arXiv:2505.20435v3 Announce Type: replace-cross Abstract: Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlook
This is why OpenAI was created Elon Musk turned down all shares when he left OpenAI because he believed nonprofits are not meant for self-enrichment. 'The reason I founded OpenAI was because I was con
Describe Seattle: I want to live near the sea and I want to live near the forest and I want to live near the mountains and I want to live near a café and I want to live near a library and I want to li
Sam Altman praised OpenAI's o1 model (version 5.5) for its earnest, persistent approach to problem-solving, comparing it to the 'little engine that could' mentality. The comment reflects Altman's pers
4⃣4⃣4⃣4⃣ Introducing DeepSeek V4 Pro, a long-context model with hybrid attention, three reasoning modes, and SOTA coding performance. AI natives can now use DeepSeek V4 Pro on Together AI and benefit
arXiv:2604.21044v1 Announce Type: new Abstract: In some complex domains, certain problem-specific decompositions can provide advantages over monolithic designs by enabling comprehension and specificat