AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Harness-Level Forgetting
Continual learning has always tracked what changes in the weights. Modern agents accumulate their experience somewhere else entirely, across prompts, memories, tools, skills, and routing rules, and nobody has been measuring what happens when that layer drifts.
DataSpace
Real organizational analytics scatters evidence across databases, structured files, long documents, and video. Existing benchmarks isolate structured querying, retrieval, or open-ended analysis, leaving heterogeneous evidence discovery, complete tabular outputs, and deterministic scoring untested together.
Molt
Agentic RL research is constant algorithm modification, and in mainstream frameworks each change threads through layers of trainer, distributed backend, and rollout glue. NVIDIA's Molt is a PyTorch-native training framework built to make that cost small.
GAMUT
Most factuality evaluation measures precision, whether the claims in an answer are correct. This Meta AI work targets the harder and mostly ignored half, completeness, meaning whether an answer covers everything it should, and packages it as the GAMUT benchmark.
RoboTTT
Recent robot foundation models run on single-step or short-history context, a strange way to attempt a five-minute assembly task. RoboTTT, from NVIDIA with Stanford and UT Austin, integrates test-time training into vision-language-action policies to scale visuomotor context to 8K timesteps, three orders of magnitude past prior policies, without growing inference latency. The longer context unlocks one-shot in-context imitation from human video, on-the-fly policy improvement, and robustness to perturbations. It improves overall performance by 87% over a single-step baseline, fully completes a ten-stage assembly task that no baseline finishes, and gains 62% from pretraining with 8K rather than 1K timesteps.
LingBot-World 2.0
Most world models fall apart after a few seconds, smearing textures and warping geometry as errors compound frame to frame. LingBot-World 2.0 from Robbyant holds 720p at 60 fps for a full hour of interaction and ships fully open.
LingBot-VLA 2.0
LingBot-VLA 2.0 is an open-source generalist embodied model from Robbyant, trained across 20 robot configurations from single-arm rigs to humanoids like Unitree G1 and Fourier GR-2. It packs 60,000 hours of curated data, 50,000 hours of real-robot trajectories plus 10,000 hours of egocentric human video, into one policy that also predicts future depth and semantic features before it acts. On 9 GM-100 tabletop tasks it beats π0.5 and GR00T N1.7 across two robot platforms and stays ahead on long-horizon mobile tasks, running at about 130 ms on a single RTX 4090D with open-sourced post-training code.
ASPIRE
ASPIRE reframes robot programming as continual, code-as-policy learning that compounds experience instead of discarding it. The system runs an open-ended loop with a closed-loop execution engine that exposes fine-grained multimodal traces, a skill library that distills validated fixes into transferable knowledge, and an evolutionary search over task sequences and control programs. It surpasses prior methods by up to 77% on perturbed manipulation and enables zero-shot generalization to unseen long-horizon tasks, with early evidence of sim-to-real transfer across different embodiments. ---
SpatialClaw
Spatial reasoning over 3D and 4D scenes is still where general vision-language models break down, because they emit a text answer directly rather than measuring anything. From NVIDIA, SpatialClaw is a training-free framework that rethinks the action interface and lets a VLM-backed agent reason through code instead. The agent writes one Python cell per step into a persistent Jupyter kernel preloaded with perception primitives and scientific libraries, then inspects intermediate results and revises its strategy across steps.
MiniMax Sparse Attention
Ultra-long context is now a core requirement for agents, codebase-scale reasoning, multimodal workflows, and persistent memory, but dense softmax attention still makes million-token deployment expensive. MiniMax Sparse Attention (MSA) tackles this by adding blockwise sparsity on top of Grouped Query Attention, with a lightweight routing branch that chooses which key-value blocks each query group should actually attend to.
Latent Spatial Memory
Video world models struggle to stay consistent over long horizons because explicit 3D memory usually requires an expensive pixel-space loop. Mirage instead stores scene information directly in diffusion latent space, using depth-guided back-projection and latent-space warping to maintain persistent spatial memory. The approach reports up to 10.57 times faster end-to-end generation and 55 times lower memory use than explicit 3D-memory baselines while improving long-horizon spatial consistency.
Beyond Scalar Rewards
Reward models usually compress a judgment into a single scalar, but this paper argues human preferences are better captured as score distributions, and proposes Z-Reward, which internalizes reasoning into a predicted distribution before scoring. A large vision-language teacher does the reasoning-heavy judgment and is distilled into a compact student for efficient deployment, with the 27B teacher reaching 89.6% human-preference accuracy and the 9B student nearly matching it at 88.6%. Used as a reinforcement learning signal, it delivers a 41.3% net preference improvement over a supervised baseline, beating GRPO and other reward methods.
OCR-Memory
Most agent memory systems compress trajectories into text summaries and hope the model remembers what matters, which is exactly where the information loss hides. OCR-Memory renders the agent's interaction history as images with indexed visual anchors, then retrieves via a locate-and-transcribe pipeline: the model scans visual memory, predicts the index of the relevant region, and the original text is fetched verbatim from a database. Older trajectories are stored as low-resolution thumbnails with active-recall up-sampling, and the method reaches SOTA on Mind2Web and AppWorld under strict context limits.
AlphaEval
Agent evaluations are drifting away from production reality. Most benchmarks use clean tasks, well-specified requirements, deterministic metrics, and retrospective curation. Production work is messier, with implicit constraints, fragmented multimodal inputs, undeclared domain knowledge, long-horizon deliverables, and expert judgment that evolves over time. This paper introduces AlphaEval, a production-grounded benchmark evaluating agents as complete products rather than model APIs.
Neural Computers
Researchers from Meta AI and KAUST propose Neural Computers (NCs), an emerging machine form that unifies computation, memory, and I/O in a single learned runtime state. Unlike conventional computers that execute explicit programs, agents that act over external environments, or world models that learn dynamics, NCs aim to make the model itself the running computer, establishing a new computing paradigm.
MedGemma 1.5
Google releases the MedGemma 1.5 technical report, introducing a 4B-parameter medical AI model that expands capabilities to 3D medical imaging (CT/MRI volumes), whole slide pathology, multi-timepoint chest X-ray analysis, and improved medical document understanding. The model achieves notable gains including a +47% macro F1 improvement on whole slide pathology and +22% on EHR question answering, positioning itself as an open foundation for next-generation medical AI systems.
NeuroSkill
MIT researchers introduce NeuroSkill, a real-time proactive agentic system that models human cognitive and emotional state by integrating Brain-Computer Interface (BCI) signals with foundation EXG models and text embeddings. Unlike reactive agents that wait for explicit commands, NeuroSkill operates proactively, interpreting biophysical and neural signals to anticipate user needs.
Phi-4-reasoning-vision-15B
Microsoft presents Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model that combines visual understanding with structured reasoning capabilities. Trained on just 200 billion tokens of multimodal data, the model excels at math and science reasoning and UI comprehension while requiring significantly less compute than comparable open-weight VLMs. The key insight is that systematic filtering, error correction, and synthetic augmentation remain the primary levers for model performance, pushing the Pareto frontier of the accuracy-compute tradeoff.
EchoJEPA
EchoJEPA is a latent predictive foundation model for echocardiography trained on 18 million echocardiograms from 300,000 patients. By learning to predict in latent space rather than pixel space, the model separates clinically meaningful anatomical signals from ultrasound noise and artifacts, producing representations that dramatically outperform existing approaches on cardiac assessment tasks.
Kimi K2.5: Visual Agentic Intelligence
Kimi K2.5 is an open-source multimodal agentic model from Moonshot AI that jointly optimizes text and vision capabilities through native multimodal pretraining on 15 trillion mixed tokens, zero-vision SFT, and joint reinforcement learning. K2.5 also introduces Agent Swarm, a parallel agent orchestration framework that dynamically decomposes complex tasks into concurrent subtasks, reducing latency by up to 4.5x over single-agent baselines.
LingBot-World: Open-Source World Simulator
LingBot-World is an open-source world simulator that evolves a video generation model into an interactive, real-time environment engine. Built on a 28B-parameter Mixture-of-Experts architecture, it achieves high-fidelity dynamics across diverse domains with sub-second latency at 16 fps, outperforming Genie 3 and Mirage 2 in dynamic degree while being fully open-source.
Learning Latent Action World Models In The Wild
Meta AI researchers address learning world models from in-the-wild videos without requiring explicit action labels, expanding beyond simple robotics simulations and video games to real-world video data with diverse embodiments and uncontrolled conditions.
UniversalRAG
UniversalRAG introduces a RAG system that handles knowledge retrieval from heterogeneous sources containing multiple data types (text, images, videos) with varying granularities. Rather than forcing diverse modalities into a single embedding space where embeddings cluster by modality rather than meaning, it uses modality-aware routing to dynamically select appropriate corpus and granularity for each query, outperforming both unimodal and unified multimodal RAG baselines across 10 benchmarks.
FACTS Leaderboard
Google introduces the FACTS Leaderboard, a comprehensive benchmark suite for evaluating LLM factuality across diverse scenarios. The leaderboard aggregates performance across four specialized sub-benchmarks to provide a holistic measure of how accurately models generate factual text.