Knowledge catalogue
📢Qwen3.7-Max just hit #3 on ITbench-AA — a fresh benchmark testing how well models handle real-world enterprise IT tasks, agentic-style. 🔧Agentic era, go with Qwen.🏃🏃 Artificial Analysis and IBM Resea
arXiv:2508.09449v2 Announce Type: replace Abstract: Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance t
arXiv:2605.28298v1 Announce Type: new Abstract: In real-world scenarios of linguistic steganalysis, tested texts usually come from unseen domains with different vocabularies, topics, writing styles, a
arXiv:2502.08938v4 Announce Type: replace Abstract: In the past decade, motivated by the putative failure of naive self-play deep reinforcement learning (DRL) in adversarial imperfect-information game
arXiv:2605.27885v1 Announce Type: new Abstract: Various approaches have been proposed to adapt Vision-Language Models (VLMs) to specialized domains for Video Question Answering, including fine-tuning
arXiv:2511.14584v3 Announce Type: replace-cross Abstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commi
arXiv:2509.26476v2 Announce Type: replace-cross Abstract: We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of program
arXiv:2603.05642v2 Announce Type: replace-cross Abstract: Open-world interactive object search in household environments requires understanding semantic relationships between objects and their surroun
arXiv:2605.28044v1 Announce Type: new Abstract: Cited RAG evaluation often treats visible sources as a grounding signal, but a real, topically relevant citation can still under-warrant the attached wo
arXiv:2605.27819v1 Announce Type: cross Abstract: Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. Th
arXiv:2605.28551v1 Announce Type: new Abstract: Many imaging problems require computing spatial transformations induced by spatially varying intensity, feature, or density fields. Canonical examples i
arXiv:2605.27479v1 Announce Type: cross Abstract: Affective computing systems are increasingly embedded in pervasive and interactive environments, such as adaptive games, assistive technologies, and r
arXiv:2512.12887v3 Announce Type: replace Abstract: 3D medical image classification is essential for modern clinical workflows. Medical foundation models (FMs) have emerged as a promising approach for
arXiv:2605.28418v1 Announce Type: new Abstract: With the rise of tabular foundation models alongside traditional models still performing well on many tasks, choosing the right model for a tabular data
arXiv:2510.22190v2 Announce Type: replace-cross Abstract: Bent radio active galactic nuclei (RAGNs) -- wide-angle tails (WATs) and narrow-angle tails (NATs) -- trace dense environments in galaxy group
arXiv:2602.13748v2 Announce Type: replace Abstract: Multimedia Event Extraction (MEE) aims to identify events and their arguments from documents that contain both text and images. It requires groundin
arXiv:2605.27718v1 Announce Type: cross Abstract: Moment-based estimation is a theoretically attractive approach to parametric inference, especially when likelihood-based estimation is unavailable, mi
arXiv:2605.28053v1 Announce Type: new Abstract: Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streamin
arXiv:2509.25582v3 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks w
arXiv:2605.28136v1 Announce Type: new Abstract: Dense semantic segmentation is essential for autonomous driving, yet many multi-modal datasets lack pixel-level annotations. The Zenseact Open Dataset (
arXiv:2602.01990v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to con
arXiv:2605.28735v1 Announce Type: new Abstract: Transparent objects are common in daily life, and it is important to understand their multilayer depth, including the transparent surface and the object
arXiv:2605.28442v1 Announce Type: cross Abstract: Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation
Mistral AI has released Mistral Vibe, an AI agent designed for long-horizon productivity and coding tasks, featuring Work mode, Code mode, a CLI, and additional capabilities. The product consolidates
arXiv:2605.27893v1 Announce Type: new Abstract: Vision Foundation Models (VFMs) have demonstrated impressive representational capabilities. However, adapting them to downstream tasks via full fine-tun
arXiv:2605.28149v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Models, but standard variants enforce non-negativity, forcing separate lat
arXiv:2605.27636v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate excellent capabilities and performance for general reasoning tasks within the general public domain, t
arXiv:2605.27760v1 Announce Type: new Abstract: Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However,
arXiv:2605.28219v1 Announce Type: cross Abstract: Unsupervised learning methods -- topic modeling, partition-based and density-based clustering -- produce data groupings without human guidance, yet ch
arXiv:2605.28122v1 Announce Type: cross Abstract: A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while th
arXiv:2605.27845v1 Announce Type: cross Abstract: Financial and economic research often relies on structured supply-chain disclosures and commercial databases. In China, supplier--customer disclosure
arXiv:2512.18444v2 Announce Type: replace-cross Abstract: Aggregating subjective preferences in social choice traditionally assumes a trusted central authority. In contrast, this paper formalises Dece
arXiv:2601.21666v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, wh
arXiv:2605.27379v1 Announce Type: new Abstract: We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and co
arXiv:2605.27756v1 Announce Type: cross Abstract: High-performance computing enables simulation of high-dimensional physical systems, but downstream analyses such as inverse problems and control remai
arXiv:2605.28490v1 Announce Type: cross Abstract: 3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together w
arXiv:2605.28036v1 Announce Type: new Abstract: Diffusion models steer conditional generation with a tunable guidance scale to trade off prompt alignment and diversity. However, existing debiasing tec
arXiv:2605.28517v1 Announce Type: cross Abstract: Stochastic gradient descent with momentum (SGDM) is one of the most widely used optimization algorithms in machine learning. While optimization proper
arXiv:2605.28073v1 Announce Type: cross Abstract: Story rewriting aims to adapt existing narratives to diverse reader preferences while preserving plot consistency and narrative coherence. Unlike conv
arXiv:2605.27393v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligne
arXiv:2605.28110v1 Announce Type: new Abstract: With the rapid development of simulation tools, the development and validation of autonomous robotic systems have become more efficient before real-worl
arXiv:2605.11325v2 Announce Type: replace-cross Abstract: Every major benchmark for LLM memory systems, LoCoMo foremost, measures whether a model answered correctly, not whether the memory system retr
arXiv:2605.27911v1 Announce Type: new Abstract: Suicide is a critical global public health challenge, causing approximately 720,000 deaths each year and calling for timely, effective prevention strate
🚨super bad news for three of the biggest IPOs in history: Companies are starting to question whether soaring AI spending is delivering meaningful returns. An AI consultant tells us a client recently s
Super excited to finally share Dynamic Workflows in Claude Code!! We built this a couple months ago, and it has slowly become a daily driver for a bunch of people at Anthropic. A few tips for getting
arXiv:2605.28179v1 Announce Type: new Abstract: Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream b
arXiv:2605.27886v1 Announce Type: new Abstract: Tactile sensing is essential for robots to achieve human-like gentle manipulation. However, existing Vision-Language-Action (VLA) models struggle to exp
arXiv:2605.27431v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across dive
arXiv:2605.27850v1 Announce Type: new Abstract: Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an
Techno Week is a thematic event or content series from Cohere, a leading AI company, likely featuring updates on technological innovations, product announcements, or industry insights shared via their
arXiv:2605.28779v1 Announce Type: new Abstract: Vision-language models (VLMs) generate fluent causal explanations, but current evaluations cannot distinguish linguistic plausibility from faithful caus
arXiv:2605.27382v1 Announce Type: cross Abstract: A key promise of pluralistic AI is behavioral adaptation: persona prompts like 'be creative' or 'be thorough' let systems respect diverse user values
arXiv:2605.28464v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have
Wall Street Journal: The CFTC moves to vacate a 5M settlement with Gemini, reversing a Biden-era enforcement action, following a lobbying campaign by the Winklevoss twins — A 5 million settlement at t
Bloomberg: The European Commission launches a full review of JD.com's €2.2B acquisition of German electronics retailer Ceconomy under its Foreign Subsidies Regulation — Chinese e-commerce firm JD.com
arXiv:2605.27901v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. Howeve
arXiv:2605.28190v1 Announce Type: new Abstract: Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding rob
arXiv:2605.28700v1 Announce Type: new Abstract: The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-
arXiv:2605.28020v1 Announce Type: new Abstract: With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The
License to stream, shaken and stirred. GeForce NOW is dialing up the espionage with the launch of 007 First Light, letting members slip into James Bond’s reimagined origin story from almost any device