Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.39567v1 Announce Type: new Abstract: Spherical harmonic descriptors of closed 3D shapes depend on the parameterization, the pose and the scale of the surface, and the standard rotation-inv...
arXiv:2609.39660v1 Announce Type: new Abstract: Generative models are transforming Bayesian computational imaging, yet the field still lacks physics-aware foundation models. Current practice falls in...
arXiv:2609.39681v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g...
arXiv:2609.39785v1 Announce Type: new Abstract: The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised...
arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past ob...
arXiv:2609.38182v1 Announce Type: cross Abstract: Avatar-based multimodal empathetic response generation has emerged as a pivotal capability in human-centric systems, aiming to recognize user emotion...
arXiv:2512.22819v2 Announce Type: replace Abstract: Panoramic depth estimation captures the complete 360$^\circ$ scene geometry, being essential for robotics and AR/VR applications. While perspective...
arXiv:2605.10360v3 Announce Type: replace Abstract: While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains...
arXiv:2607.09351v2 Announce Type: replace Abstract: Severe downsampling makes single image super-resolution (SISR) an ill-posed problem, in which the language-guided multi-modal methods are especiall...
arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-actio...
arXiv:2607.22465v3 Announce Type: replace Abstract: Modern enterprise agent deployments consist of a heterogeneous pool of large language models (LLMs) having diverse capabilities and cost. Existing...
The paper introduces VHOP, a data generation framework and benchmark for visual agentic search, and VHOP-Router, an end‑to‑end training pipeline that turns a standard embedding model into an autoregressive multi‑step retriever operating directly in visual latent space. VHOP-Router eliminates the need for intermediate text queries, boosting retrieval accuracy from under 5% to 76.3% and improving task success rates by 52.7% while dramatically reducing token usage and API payloads. The approach generalizes to unseen difficulty levels and realistic test sets, offering an efficient solution that preserves native LLM capabilities.
Cryo-Bench is a new benchmark that evaluates foundation models for cryosphere mapping, comprising six semantic‑segmentation datasets across five cryospheric components (supraglacial debris, glacial lakes, sea ice, calving fronts, and Antarctic ice‑shelf extent). The benchmark includes multispectral, RGB, and SAR observations from under‑represented regions and tests thirteen geo‑foundation models alongside U‑Net and Vision Transformer baselines. Results show that with frozen encoders U‑Net slightly outperforms TerraMind, but the difference is not statistically significant; fine‑tuning with learning‑rate optimization can dramatically improve performance for some models, while in few‑shot scenarios several foundation models retain over 90 % of their full‑label accuracy.
arXiv:2608.06912v2 Announce Type: replace Abstract: Selecting the top-$k$ elements is a fundamental operation for inducing sparsity in large-scale models and optimization problems, enabling robust ex...
The paper introduces the concept of stale binding, where large language models (LLMs) answer with outdated values despite having newer information in context. It presents Controlled In-Context Memory (CICM), a benchmark to track and test the use of updated information in conversations and agent logs. Experiments on open‑source models reveal an attention drift mechanism that favors old values, and the authors propose a simple attention‑redirecting intervention that largely corrects these errors without harming correct answers.
arXiv:2605.16679v3 Announce Type: replace-cross Abstract: End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density,...
arXiv:2609.38810v1 Announce Type: cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual sig...
arXiv:2609.38578v1 Announce Type: cross Abstract: Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing state-of-the-art...
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-...
GroundAnything is a 4‑B parameter grounding foundation model that combines autoregressive and diffusion approaches to achieve fast parallel decoding while maintaining precise visual grounding. By treating grounding as visual evidence extraction and using blockwise denoising, it allows spatial hypotheses to be generated in parallel and refined iteratively. The model outperforms existing state‑of‑the‑art methods on 30 grounding benchmarks, achieving 72.42% accuracy with its autoregressive variant and 61.75% with entropy‑guided decoding, while also offering significant speedups through optional self‑speculative decoding.