Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2605.30454v2 Announce Type: replace-cross Abstract: Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success...
arXiv:2609.39953v1 Announce Type: new Abstract: Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computa...
arXiv:2609.38368v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly reason over visual evidence that is cropped, segmented, retrieved, or revealed over time. Yet most VQA bench...
arXiv:2609.38620v1 Announce Type: new Abstract: Neural implicit representations have had a significant impact on scene reconstruction by enabling robots to build continuous, differentiable, and high-...
arXiv:2609.38823v1 Announce Type: new Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becau...
arXiv:2609.39021v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially improved the reasoning ability of multimodal language models through verifiable rewards and increasingly...
arXiv:2609.39116v1 Announce Type: new Abstract: Prior-free 6D object pose tracking seeks to recover the trajectory of an unseen object from a single RGB video without object-specific CAD models, pose...
arXiv:2609.39132v1 Announce Type: new Abstract: We study few-step video generation, i.e., distilling a multi-step video generator, which typically requires tens of sampling steps, incurring substanti...
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...
arXiv:2609.39563v1 Announce Type: new Abstract: Existing video language models encode sampled RGB frames independently, so a long video must either exhaust the token budget or drop the changes betwee...
arXiv:2609.39649v1 Announce Type: new Abstract: Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to...
arXiv:2609.39748v1 Announce Type: new Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...
arXiv:2606.27223v3 Announce Type: replace Abstract: Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometric...
arXiv:2609.31665v2 Announce Type: replace Abstract: Action anticipation predicts future human actions from partial video under incomplete context and temporal uncertainty. Recent systems introduce la...
arXiv:2609.35490v2 Announce Type: replace Abstract: Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning....
arXiv:2609.38923v1 Announce Type: new Abstract: Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files wit...
arXiv:2609.39964v1 Announce Type: new Abstract: Multi-modal integrated sensing and communication (ISAC) enables environmental perception and reliable connectivity for intelligent wireless networks. D...
The paper presents a method for turning expert diagnoses of verification failures into reusable guidance for coding agents. By combining executable language definitions in the K framework with a set of procedures for constructing specifications, repairing proofs, and auditing their adequacy, the authors achieve a 164/164 success rate on the HumanEval benchmark after two targeted repairs. They further demonstrate that audits can detect defects missed by successful proofs and evaluate the approach on KleverBench and Optimism proofs, highlighting both progress and remaining challenges.
Hermes introduces a family of harnesses that give models control over how they allocate and reuse context windows during inference, a capability termed contextual reasoning. The accompanying Hermes‑Learn framework trains models in two stages to develop these decision‑making skills, enabling them to scale performance with additional compute at test time. Experiments show that while large models naturally benefit, smaller open‑source models can close the performance gap through this training, with gains generalizing across benchmarks, extrapolating beyond trained compute, and transferring to other scaling methods.
arXiv:2609.38523v1 Announce Type: cross Abstract: Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle co...