Superficial Beliefs in LLM Decision-Making
arXiv:2606.11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic u
Knowledge catalogue
arXiv:2606.11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic u
arXiv:2606.11032v1 Announce Type: new Abstract: Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution
arXiv:2606.10393v1 Announce Type: new Abstract: Credit-card fraud detection is difficult because fraudulent transactions are rare, costly, and unevenly distributed. Strong gradient-boosted tree models
arXiv:2606.10423v1 Announce Type: new Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference
arXiv:2606.11045v1 Announce Type: new Abstract: Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly l
arXiv:2603.11250v2 Announce Type: replace-cross Abstract: Accurate modeling of gas flow through porous media is critical for many technological applications, including reservoir performance prediction
arXiv:2606.09825v1 Announce Type: cross Abstract: Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substan
arXiv:2606.07643v1 Announce Type: cross Abstract: Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their a
arXiv:2606.08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance va
arXiv:2606.09033v1 Announce Type: new Abstract: The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers,
arXiv:2511.04124v3 Announce Type: replace Abstract: Symbolic regression (SR) models complex systems by discovering mathematical expressions that capture underlying relationships in observed data. Howe
arXiv:2606.07970v1 Announce Type: cross Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with o
Gemini 3.5 Live Translate is Google's latest audio model delivering near real-time speech-to-speech translation in over 70 languages. The model automatically detects 70+ languages and generates smooth
arXiv:2606.08594v1 Announce Type: new Abstract: Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model ca
arXiv:2601.04498v2 Announce Type: replace-cross Abstract: Infographics are composite visual artifacts that combine data visualizations with textual and illustrative elements to communicate information
arXiv:2510.20182v2 Announce Type: replace Abstract: Pedestrian simulation traditionally relies on expert-tuned, hand-crafted models that limit scalability and generalization. Meanwhile, large-scale vi
arXiv:2508.00724v2 Announce Type: replace-cross Abstract: The increasing demand for flexible automation has accelerated the adoption of heterogeneous automated guided vehicles (AGVs). This work invest
arXiv:2510.17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de
arXiv:2606.07968v1 Announce Type: cross Abstract: Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's quest
arXiv:2602.15253v2 Announce Type: replace Abstract: Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transf
arXiv:2606.08034v1 Announce Type: cross Abstract: Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing s
arXiv:2606.07608v1 Announce Type: cross Abstract: We present a systematic study of fine-tuning OpenAI's Whisper large-v3 for Swiss German ASR, using 1,367 hours of broadcast speech paired with Standar
arXiv:2606.09019v1 Announce Type: cross Abstract: Codec-based autoregressive (AR) speech language models have achieved strong text-to-speech (TTS) quality by modeling speech as sequences of discrete a
arXiv:2606.07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-hand
arXiv:2606.07872v1 Announce Type: new Abstract: When a multimodal large language model answers a visual reasoning question correctly, is the prediction actually supported by the task-critical visual e
arXiv:2602.01357v2 Announce Type: replace Abstract: Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into stro
arXiv:2606.07965v1 Announce Type: new Abstract: Large Visual Language Models (LVLMs) have achieved remarkable success in vision tasks. However, the significant differences between industrial and natur
arXiv:2606.08841v1 Announce Type: new Abstract: Text-to-image diffusion models are increasingly deployed in open-ended creative contexts, yet their outputs remain impersonal, optimized for aggregate a
arXiv:2606.06526v1 Announce Type: new Abstract: Large language models have made substantial progress on mathematical reasoning, but existing benchmarks typically evaluate well-specified problems with
arXiv:2606.07207v1 Announce Type: cross Abstract: Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this in
arXiv:2606.07135v1 Announce Type: new Abstract: Huntington's disease (HD) is a progressive neurodegenerative disorder that affects motor, cognitive, and behavioral functions, where accurate characteri
arXiv:2601.12375v3 Announce Type: replace-cross Abstract: Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Ne
arXiv:2602.11201v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these st
arXiv:2606.06624v1 Announce Type: new Abstract: In the current era of deep learning and especially generative models, there is significant investment in training very large generative models. Thus far
arXiv:2606.06941v1 Announce Type: new Abstract: Large language models (LLMs) now solve a wide range of expert-level exams at or above human level, yet remain brittle on specialised, evidence-intensive
arXiv:2606.06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vul
arXiv:2606.06891v1 Announce Type: new Abstract: Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or pr
arXiv:2606.07167v1 Announce Type: cross Abstract: Meaningful multilingual evaluation must test models in the target language and educational context. Urdu, spoken by more than 230 million people, lack
arXiv:2606.06538v1 Announce Type: new Abstract: In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types
arXiv:2606.05383v1 Announce Type: cross Abstract: Can artificial intelligence (AI) refute economic theory? I document experiments in which I asked several AI models (Gemini, Refine, Claude, and ChatGP
arXiv:2602.13255v2 Announce Type: replace Abstract: We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models. Existing benchmarks measure tas
arXiv:2606.06322v1 Announce Type: new Abstract: GUI agents - vision-based models that control desktops, web browsers, and mobile devices through graphical user interfaces - promise to automate a wide
Ideogram 4.0 is a frontier text-to-image foundation model released as an open-weight model with a commercial license. The model delivers frontier-grade text rendering across languages, bounding-box la
arXiv:2606.05389v1 Announce Type: new Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations. Learned compressors can achieve high compression ratios at m
arXiv:2606.05403v1 Announce Type: cross Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions. Whether they evaluate the qual
arXiv:2601.21288v2 Announce Type: replace-cross Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and
arXiv:2606.05354v1 Announce Type: new Abstract: Retinal blood vessel segmentation plays a vital role in the early detection of diabetic retinopathy and glaucoma. While recent deep learning models have
arXiv:2606.05535v1 Announce Type: new Abstract: Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and ans
Google's May 2026 AI updates center on the new 'agentic' era, featuring the Gemini 3.5 model and Gemini Omni for advanced reasoning and creation. Gemini Omni is a new model that can create anything fr
arXiv:2602.09464v2 Announce Type: replace-cross Abstract: Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a
arXiv:2510.11194v3 Announce Type: replace Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current met
arXiv:2606.04072v1 Announce Type: cross Abstract: Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic desi
arXiv:2606.04915v1 Announce Type: new Abstract: Large language models reach 50 to 70% accuracy on causal reasoning benchmarks such as CLadder, but it is unclear whether this reflects structural reason
arXiv:2606.04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-
arXiv:2606.04282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, a
arXiv:2606.04019v1 Announce Type: cross Abstract: Recent studies on sensor-language alignment have shown that two-stage frameworks can improve the semantic modeling ability of wearable-sensor human ac
Gemma4 is a language model available through Ollama's model library that users can download and run locally. The entry likely provides information about the model's specifications, capabilities, and h
arXiv:2606.04612v1 Announce Type: new Abstract: Large Language Models (LLMs) are vulnerable both to hallucination and adversarial manipulation. Although these problems are closely related, existing de
arXiv:2606.04339v1 Announce Type: new Abstract: Computational models of epilepsy promise patient-specific treatment design, but most optimization workflows still search for parameters that perform wel
Nemotron 3 Ultra, NVIDIA's advanced language model, is now accessible through Vercel's AI Gateway, enabling developers to integrate this model into their applications alongside other LLM options. The