Knowledge catalogue
arXiv:2606.29869v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a key technique for compressing Large Language Models (LLMs), yet methods relying on a single KL objective often fail t
arXiv:2606.29925v1 Announce Type: new Abstract: As deep learning models are increasingly deployed in high-stakes applications, providing well-calibrated uncertainty estimates has become as critical as
arXiv:2606.29984v1 Announce Type: new Abstract: Reinforcement Learning (RL) is an important paradigm for improving the reasoning capabilities of Vision-Language Models (VLMs). However, directly applyi
arXiv:2606.30457v1 Announce Type: new Abstract: We study behavior prompting, a paradigm that enables robots to perform new tasks at inference time given a single human demonstration, which we call a b
arXiv:2606.29201v1 Announce Type: cross Abstract: Behavior-cloned policies often learn multiple behavior modes from demonstration datasets, including modes that are unsafe or otherwise undesired at de
Being at the launch of Cybercab two years ago was magic. A decade from now there will be millions of these things rolling around the world. The war over autonomous vehicles is on, as everyone in San F
arXiv:2606.29134v1 Announce Type: new Abstract: Rapid flood mapping is critical for emergency response, yet optical imagery is often unusable during major flooding and single-temporal SAR is ambiguous
arXiv:2606.30319v1 Announce Type: new Abstract: Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscien
Bridgewater, one of the worlds largest hedge funds, a Tinker customer talks through how they've carefully fine-tuned a model focused on what makes interesting financial news. Their fine-tuned model is
arXiv:2606.29102v1 Announce Type: cross Abstract: Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to
arXiv:2606.29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and whe
arXiv:2606.30044v1 Announce Type: new Abstract: A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models b
arXiv:2606.28707v1 Announce Type: new Abstract: Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value fun
arXiv:2606.28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from c
arXiv:2606.23671v2 Announce Type: replace Abstract: Prior work shows that large language models (LLMs) exhibit introspective capability on benign tasks. We extend the question to safety contexts and e
arXiv:2606.29689v1 Announce Type: new Abstract: Open-ended aesthetic critique is a challenge for multimodal large language models (MLLMs): unlike multiple-choice aesthetic benchmarks, it has no single
arXiv:2606.30236v1 Announce Type: new Abstract: Medication errors, particularly dosing errors in clinical trials (CT), can lead to patient harm, adverse drug events and worse patient outcomes. Dosing
arXiv:2606.28360v1 Announce Type: cross Abstract: University students often struggle to navigate complex academic policies, leading to advising bottlenecks and delayed access to critical information.
arXiv:2606.28815v1 Announce Type: cross Abstract: Mathswitch is an open-source project that imports mathematical concept records from sources such as Wikidata, Wikipedia, MathWorld, Encyclopedia of Ma
arXiv:2606.29116v1 Announce Type: new Abstract: Large Language Models (LLMs) are rapidly being adopted in low-code and no-code automation platforms, where non-expert users design workflows that combin
arXiv:2606.30318v1 Announce Type: new Abstract: General-purpose robot policies should be modeled as dynamical systems, yet many VLA and generative imitation policies still rely on present observations
arXiv:2606.29805v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, ca
arXiv:2606.29136v1 Announce Type: cross Abstract: Event cameras capture sparse brightness changes with high temporal resolution and high dynamic range, compensating for the deficiencies of the convent
arXiv:2603.17621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, st
arXiv:2606.30268v1 Announce Type: new Abstract: Sim-to-real policy transfer -- deploying policies trained in simulation in the real world -- is a promising paradigm for scaling robot manipulation with
arXiv:2606.29801v1 Announce Type: new Abstract: Text-to-image diffusion models remain vulnerable to adversarial prompts that elicit disallowed content, motivating reliable inference-time controls. A p
arXiv:2606.29812v1 Announce Type: new Abstract: Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cr
arXiv:2606.29517v1 Announce Type: new Abstract: Robot imitation learning often relies on costly robot demonstrations, while abundant action-free visual demonstrations, such as human videos, are diffic
arXiv:2606.29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same pol
arXiv:2606.29898v1 Announce Type: cross Abstract: Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are
arXiv:2606.29949v1 Announce Type: cross Abstract: H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides
arXiv:2512.20117v2 Announce Type: replace Abstract: Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by integrating auditory and visual cues. However, existi
arXiv:2606.29280v1 Announce Type: cross Abstract: We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without t
arXiv:2606.30414v1 Announce Type: new Abstract: Distillation and Reinforcement Learning (RL) fine-tuning are the primary pillars of diffusion post-training. While traditionally studied in isolation, t
arXiv:2512.07778v2 Announce Type: replace Abstract: Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches su
arXiv:2503.00539v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). Howe
arXiv:2606.29522v1 Announce Type: cross Abstract: A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with
arXiv:2606.30626v1 Announce Type: new Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish hi
arXiv:2606.30345v1 Announce Type: cross Abstract: Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning
arXiv:2606.30183v1 Announce Type: new Abstract: Medical image registration benefits significantly from deep learning, yet existing approaches often lack physical explainability and fine-grained deform
arXiv:2606.29198v1 Announce Type: new Abstract: As the most perceptually powerful Face Video Super-Resolution (FVSR) method, existing works in Generative FVSR (GFVSR) mainly exploit the generative pri
arXiv:2606.29820v1 Announce Type: cross Abstract: In complex continuous-control reinforcement learning tasks, multimodal optimal actions often coincide with uncertain, multimodal return distributions,
arXiv:2602.23135v2 Announce Type: replace-cross Abstract: Edge classification on directed dynamic graphs requires modeling interactions between source and destination nodes exhibiting asymmetrical beh
arXiv:2606.30531v1 Announce Type: new Abstract: Tool-augmented language-model agents are often evaluated by whether they select the correct tool, produce valid API arguments, and complete the requeste
arXiv:2606.29424v1 Announce Type: new Abstract: Model routing balances solution accuracy and computational cost by selecting among models of varying capabilities. While recent multi-round frameworks i
arXiv:2603.09785v3 Announce Type: replace Abstract: This paper introduces an updated and combined version of the bidirectional English-German EPIC-UdS (spoken) and EuroParl-UdS (written) corpora conta
arXiv:2512.21545v2 Announce Type: replace Abstract: Object removal must prevent the masked target from reappearing and reconstruct the occluded background with structural and contextual fidelity, rath
arXiv:2606.30152v1 Announce Type: cross Abstract: Contextual language models conflate grammatical gender and social semantic bias in gendered languages such as Spanish. Existing gender debiasing appro
arXiv:2606.28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and sur
arXiv:2512.07287v3 Announce Type: replace-cross Abstract: As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is
arXiv:2509.21530v2 Announce Type: replace Abstract: Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples. W
arXiv:2606.29980v1 Announce Type: new Abstract: Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional
arXiv:2604.02714v2 Announce Type: replace Abstract: End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies t
arXiv:2606.28476v1 Announce Type: new Abstract: High-precision humanoid control is limited by target-domain dynamics mismatch, where the same control objective can induce different realized motions un
arXiv:2602.12155v2 Announce Type: replace Abstract: Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning
arXiv:2606.29064v1 Announce Type: cross Abstract: The unfairness of recommender systems has become a topic of concern due to its significant social and ethical implications. Although existing works ha
arXiv:2606.29350v1 Announce Type: cross Abstract: Vision-language models and vision-language action models endow the robot with unprecedented capabilities. However, the input of video and high-resolut
arXiv:2606.29319v1 Announce Type: new Abstract: Image-based Virtual Try-On (IVTON) has greatly advanced through diffusion models, yet existing methods require many sampling steps and depend on masks w
arXiv:2606.30376v1 Announce Type: cross Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing
arXiv:2606.29917v1 Announce Type: new Abstract: Instance-Specific Image-Goal Navigation (InstanceImageNav) requires a robot to navigate toward the exact object instance depicted in a query image. Exte