Knowledge catalogue
arXiv:2605.02398v1 Announce Type: cross Abstract: As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not kn
arXiv:2602.11083v2 Announce Type: replace Abstract: Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-
arXiv:2605.00842v1 Announce Type: cross Abstract: Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite
arXiv:2602.22480v2 Announce Type: replace-cross Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-eva
arXiv:2602.18700v2 Announce Type: replace-cross Abstract: LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial
The cars rolling off production lines right now are filled with old ideas. From beginning to end, the creation of a new vehicle can take five years or longer - which is plenty of time for a lot of tas
arXiv:2605.02038v1 Announce Type: new Abstract: Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-w
arXiv:2603.15949v3 Announce Type: replace Abstract: Large Language Models have demonstrated strong multilingual fluency, yet fluency alone does not guarantee socially appropriate language use. In high
arXiv:2605.00592v1 Announce Type: new Abstract: In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as
arXiv:2510.18900v2 Announce Type: replace-cross Abstract: Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing com
arXiv:2509.24621v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc
arXiv:2605.00645v1 Announce Type: new Abstract: Clinical time-series forecasting is increasingly studied for decision support, yet standard aggregate metrics can obscure whether a model is actually us
arXiv:2603.02727v4 Announce Type: replace Abstract: Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers
arXiv:2605.00267v1 Announce Type: new Abstract: As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this
arXiv:2602.04212v2 Announce Type: replace Abstract: Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier
arXiv:2605.00051v1 Announce Type: new Abstract: Anticipating traffic accidents is a critical yet unresolved problem for autonomous driving, hindered by the inherent complexity of modeling interactions
arXiv:2605.00050v1 Announce Type: cross Abstract: Traffic accidents are routinely documented in textual reports, yet physically grounded accident reconstruction remains difficult because detailed scen
arXiv:2605.00505v1 Announce Type: cross Abstract: Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented g
arXiv:2604.01707v2 Announce Type: replace Abstract: Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game pla
arXiv:2605.00347v1 Announce Type: cross Abstract: Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has e
Open sources harnesses powered by open source models I hear this take (usually from the model labs), but that will just mean more people turn to open source models, no? They’re already cheaper, if the
arXiv:2605.00814v1 Announce Type: new Abstract: While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a 'Visual Signal Dilution' p
arXiv:2411.02327v4 Announce Type: replace Abstract: In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long vi
arXiv:2601.06600v2 Announce Type: replace Abstract: Short-video platforms have become major channels for misinformation, where deceptive claims frequently leverage visual experiments and social cues.
arXiv:2602.18196v3 Announce Type: replace Abstract: Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of
arXiv:2601.07349v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GR
arXiv:2605.00798v1 Announce Type: cross Abstract: Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose Ru
arXiv:2605.00444v1 Announce Type: new Abstract: Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded percept
arXiv:2505.18875v4 Announce Type: replace Abstract: Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. B
arXiv:2605.00684v1 Announce Type: new Abstract: Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. R
arXiv:2511.03928v5 Announce Type: replace Abstract: We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task p
arXiv:2605.00140v1 Announce Type: cross Abstract: We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit
arXiv:2605.00015v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TS
arXiv:2605.00300v1 Announce Type: cross Abstract: Public inference benchmarks compare AI systems at the model and provider level, but the unit at which deployment decisions are actually made is the en
arXiv:2605.00297v1 Announce Type: cross Abstract: Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE heade
Try Grok Grok 4.3 just became the smartest AI in the world at law and money It took #1 on TWO brutal private tests no other model could win on “Vals AI” benchmarks #1 CaseLaw (v2) - 79.31% accuracy Pr
we're on an Open Model mission to help builders create world class agents >20x cheaper than what they have today a couple things have become evident recently: 1. The age of the token subsidy is being
arXiv:2605.00226v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymakin
AI will create more jobs than any other technology in history. The doomers' fundamental error isn't just the lump of labor fallacy. It's deeper than that. They assume a finite problem space. This is t
Brian Moore's interactive clock comparison tool demonstrates the significant performance gaps and inconsistencies across different AI systems when performing the seemingly simple task of displaying ti
I hear this take (usually from the model labs), but that will just mean more people turn to open source models, no? They’re already cheaper, if they have similar performance (because they’re less coup
Sakana AI Labs has developed Fugu, a multi-agent orchestration system designed to function as a foundation model. The system likely enables coordinated interaction between multiple AI agents to improv
the same model in a different harness can yield much different performance! we've seen this on a few different occasions now - we took gpt-5.2-codex from 52.8% to 66.5% on Terminal-Bench 2.0 (Top 30 t
Grok Voice is used by Starlink right now Grok Voice brutally dominates the top of the τ-voice Bench Grok scores 67.3%, while Gemini sits at 43.8% and GPT Realtime at 35.3% This is a massive lead over
This episode features Warren Smith discussing the decline of critical thinking in contemporary society, likely exploring how factors such as social media, institutional education, or cultural trends h
arXiv:2604.28177v1 Announce Type: new Abstract: We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS featur
arXiv:2604.28078v1 Announce Type: new Abstract: Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors
arXiv:2604.09718v2 Announce Type: cross Abstract: LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhi
arXiv:2604.26969v1 Announce Type: cross Abstract: Modern large-scale recommendation systems are typically constructed as multi-stage pipelines, encompassing pre-ranking, ranking, and re-ranking phases
All the Doomers and hawks are lining up behind this distillation 'attack' farce because they want to see open source banned. It's really as simple as that. They want to take away your right to choose,
arXiv:2604.26986v1 Announce Type: new Abstract: We introduce a novel task of digital battery passport (DBP) conformance classification and introduce the first public benchmark for the task: BatteryPas
arXiv:2604.27699v1 Announce Type: new Abstract: Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework e
arXiv:2604.27083v1 Announce Type: new Abstract: RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert cap
arXiv:2604.27389v1 Announce Type: cross Abstract: In recent years, Multimodal Large Language Models (MLLMs) have achieved remarkable progress on a wide range of multimodal benchmarks. Despite these ad
arXiv:2604.27929v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs), understanding their personality representation mechanisms has become critical. As a novel
arXiv:2604.27987v1 Announce Type: new Abstract: Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets.
arXiv:2604.28034v1 Announce Type: new Abstract: The syntactic structure of a sentence can be represented as a tree where edges indicate syntactic dependencies between words. When that structure is a s
arXiv:2602.00095v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) hold significant promise for revolutionizing traditional education and reducing teachers' workload. H
arXiv:2604.27092v1 Announce Type: new Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods
arXiv:2304.14352v2 Announce Type: replace-cross Abstract: Currently, there is a trend for the wider public to rely on LLMs for financial or legal consultation, medical and mental support (Chatterji et