Knowledge catalogue
arXiv:2606.29481v1 Announce Type: cross Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets
arXiv:2606.29254v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate broad reasoning abilities but struggle with accuracy and reliability in specialized domains such as travel, whe
arXiv:2510.16325v3 Announce Type: replace Abstract: Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity
arXiv:2606.30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling b
arXiv:2508.14483v4 Announce Type: replace Abstract: We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to c
arXiv:2606.30045v1 Announce Type: new Abstract: Interactive video generation systems for camera-controlled world exploration roll out growing sequences of latent video frames, entangling state transit
arXiv:2606.29712v1 Announce Type: new Abstract: Large language models achieve high reasoning performance via explicit chain-of-thought and reinforcement learning, but require long output sequences and
arXiv:2606.28899v1 Announce Type: new Abstract: Accurate 6-DoF object pose estimation is fundamental to robotic manipulation, yet vision-based methods often fail under occlusion, poor lighting, and re
arXiv:2601.13602v3 Announce Type: replace-cross Abstract: This paper introduces an analytical approach to quantifying and optimizing the distributional discrepancy in generative diffusion models. For
arXiv:2606.27405v1 Announce Type: cross Abstract: Deep learning has shown significant potential in medical image analysis, particularly for disease detection using MRI scans. Accurate and early diagno
arXiv:2606.27732v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) recover masked tokens in parallel, offering significant speedups over autoregressive (AR) generation. Howev
arXiv:2511.02340v3 Announce Type: replace Abstract: Chronic Kidney Disease (CKD) affects nearly 10% of the global population and often progresses to end-stage renal failure. Accurate prognosis predict
arXiv:2606.27964v1 Announce Type: new Abstract: Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video
arXiv:2606.27748v1 Announce Type: cross Abstract: Transformer models rely on attention mechanism to capture long-range dependencies but suffer from quadratic complexity, limiting their scalability to
arXiv:2606.27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern larg
arXiv:2606.27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncer
arXiv:2606.27617v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approxim
arXiv:2603.05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters
arXiv:2606.27773v1 Announce Type: new Abstract: Image-based virtual try-on has emerged as a compelling task in e-commerce and augmented reality, yet existing methods struggle to simultaneously preserv
Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding This is an interesting new open weights (MIT licensed) model, the first model release from DeepReinforce. [...] with variants including 9B Dense, 3
arXiv:2606.28094v1 Announce Type: cross Abstract: Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which ar
arXiv:2606.27745v1 Announce Type: new Abstract: Panoramic images capture the complete visual sphere in a single frame, providing spatial context unattainable by conventional cameras. Yet this complete
arXiv:2606.27978v1 Announce Type: cross Abstract: Pixel-space continuous-token autoregressive (AR) generation directly models images as sequences of raw pixel patches, avoiding discrete tokenization o
arXiv:2606.28220v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving nonlinear partial differential equations (PDEs), including battery
arXiv:2512.21970v2 Announce Type: replace Abstract: While Vision-Language-Action (VLA) models excel in generalist manipulation, they often lack fine-grained spatial awareness and show limited viewpoin
arXiv:2606.27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations. Improving these policies with reinforcement learning (RL)
arXiv:2510.03117v2 Announce Type: replace Abstract: This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized a
arXiv:2606.27655v1 Announce Type: new Abstract: Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are o
arXiv:2606.27538v1 Announce Type: cross Abstract: We introduce the context-ready transformer, a new recurrent neural network architecture built from a D-layer transformer block that pre-contextualizes
arXiv:2505.05517v3 Announce Type: replace Abstract: Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on po
arXiv:2606.27632v1 Announce Type: new Abstract: As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We arg
arXiv:2606.26560v1 Announce Type: new Abstract: Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new conte
arXiv:2606.26938v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have f
arXiv:2606.26629v1 Announce Type: cross Abstract: Weight-space regularization methods such as Elastic Weight Consolidation (EWC) are the standard approach to catastrophic forgetting in continual learn
arXiv:2606.27326v1 Announce Type: cross Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fl
arXiv:2603.06480v2 Announce Type: replace Abstract: Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capabili
arXiv:2606.27275v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly critical to digital library workflows, yet their ability to process historical language remains poorly und
arXiv:2606.27192v1 Announce Type: new Abstract: The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermediate-layer features to a frozen pre
arXiv:2606.26839v1 Announce Type: cross Abstract: Learning robust navigation policies directly from visual observations remains a fundamental challenge in vision-based robotic navigation. In end-to-en
arXiv:2606.27144v1 Announce Type: new Abstract: Reliable action generation for multi-stage robotic manipulation remains challenging for Vision-Language-Action (VLA) models. While existing flow-matchin
arXiv:2606.26797v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities
arXiv:2606.26175v1 Announce Type: new Abstract: Reinforcement learning (RL) for robotic manipulation often requires manually designing a dense reward function, which is difficult to tune and often fra
arXiv:2606.26734v1 Announce Type: cross Abstract: The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We presen
arXiv:2606.27223v1 Announce Type: new Abstract: Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically
arXiv:2606.26800v1 Announce Type: new Abstract: Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly ch
arXiv:2601.20381v3 Announce Type: replace Abstract: Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limi
arXiv:2603.14717v2 Announce Type: replace Abstract: Generating novel protein sequences that respect a family's statistical constraints typically requires training deep generative models on thousands t
arXiv:2606.27313v1 Announce Type: new Abstract: A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more efficient training. However, repre
arXiv:2606.24903v1 Announce Type: new Abstract: Deciding when to stop collecting labeled examples is a fundamental but undertheorized problem in applied machine learning. The saturation index S(K) = o
arXiv:2606.25985v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong potential for general-purpose robot manipulation, but their inference latency remains a major obst
arXiv:2606.25207v1 Announce Type: cross Abstract: Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding
arXiv:2606.25128v1 Announce Type: cross Abstract: Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs
arXiv:2606.25674v1 Announce Type: new Abstract: LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone
arXiv:2606.25432v1 Announce Type: cross Abstract: Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost wh
arXiv:2606.25488v1 Announce Type: new Abstract: Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational
arXiv:2606.26003v1 Announce Type: new Abstract: Automatic speech and language technologies are still heavily biased toward high-resource languages, limiting their applicability to dialectal and low-re
arXiv:2606.25198v1 Announce Type: new Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-base
arXiv:2411.15490v2 Announce Type: replace Abstract: Acute ischemic stroke (AIS) requires time-critical decision-making, where inaccurate interpretation of neuroimaging findings can lead to irreversibl
arXiv:2606.19157v2 Announce Type: replace-cross Abstract: AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear wh
arXiv:2606.24998v1 Announce Type: new Abstract: Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier cont