Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
arXiv:2608.00135v1 Announce Type: new
Abstract: Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer vision benchmarks. Building on JONES-19, a small-size ...
Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression
arXiv:2608.00129v1 Announce Type: new
Abstract: Knowledge distillation (KD) is a widely utilized technique for transferring knowledge from a large model (the teacher) to a smaller model (the student). Owing to its flexibility and broad applicability, KD has been extensively applied in the compressi...
MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing
arXiv:2608.00107v1 Announce Type: new
Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recover from failure. These meta-decisions affect not only task success but a...
Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
arXiv:2608.00106v1 Announce Type: new
Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it. A controller may answer directly, decompose a request, retrieve evidence, execute code, delegate to a specialist, or verify an...
Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models
arXiv:2608.00019v1 Announce Type: new
Abstract: Deploying large language models (LLMs) for operations research (OR) tasks remains challenging because correctness depends on a coherent modeling process, not merely a correct final answer. Standard autoregressive generation operates on a myopic policy...
Open-Weight Models Aren’t Enough. We Need Truly Open Source AI Models for Science and Society.
As Chinese AI closes the capability gap, Washington and Silicon Valley debate open-weight models. Stanford HAI's James Landay says it's the right conversation framed the wrong way.
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure.
The post Orchard: An open framework for scalable a...
LLM Framework for Discovering Major Mathematical Conjectures: AI's Quest for the Next Riemann Hypothesis
arXiv:2607.28632v1 Announce Type: new
Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the systematic generation and validation of conjectures with substantial mathematical potential remains unavailable. We present a three stage pipeline for...
Topology-Aware Data Movement for Disaggregated GPU Inference
arXiv:2607.28633v1 Announce Type: new
Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly. When prefill and decode run on separate GPU pools, the KV cache must be transferred between them. For a 70B model this is 2.6 GB per request,...
Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems
arXiv:2607.28665v1 Announce Type: new
Abstract: Automated driving systems (ADSs) are becoming ubiquitous. Future Software Defined Vehicles (SDVs) may be able to run multiple ADSs, both native and aftermarket such as Comma.ai's Openpilot. Monitoring systems to independently verify which automated dr...
Guarantees on Dynamical System Distinguishability for LLM Token Generation
arXiv:2607.28667v1 Announce Type: new
Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs. Despite the empirical ...
LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment
arXiv:2607.28669v1 Announce Type: new
Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rather than in its weights. Where LoRA adds an update of low rank to weight matrices, LARA reads the h...
OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems
arXiv:2607.28629v1 Announce Type: new
Abstract: The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural understanding of Agentic AI, particularly in separating inference, orchestration, and execution layers...
ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning
arXiv:2607.28642v1 Announce Type: new
Abstract: Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under bounded context windows, the core bottleneck is not trajectory compres...
TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter
arXiv:2607.28657v1 Announce Type: new
Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reform...
Hierarchical Copula-Gumbel-Top-\texorpdfstring{$K$}{K} Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws
arXiv:2607.28670v1 Announce Type: new
Abstract: A stochastic Gumbel-Top-$K$ router defines, for every token of a mixture-of-experts (MoE) model, a \emph{routing law}: a distribution over ordered expert lists and mixture weights. We ask which \emph{joint} distributions over the routing choices of di...
Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding
arXiv:2607.27269v1 Announce Type: new
Abstract: Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (KV) cache and reduce decoding memory traffic. Yet most capable open checkpoints use multi-head or g...
PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective
arXiv:2607.27265v1 Announce Type: new
Abstract: Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Platform (DSP) bidding for advertisers, and Ad Exchange conducting auctions between them. Traditional ...
DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series
arXiv:2607.27263v1 Announce Type: new
Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where it matters most, such as in healthcare, policy evaluation, and climate ...
Recursive transformers for semiconductor thermo-mechanical reliability
arXiv:2607.27251v1 Announce Type: new
Abstract: Transformer-based surrogate models are increasingly used to replace expensive first-principles simulation in engineering design. But conventional transformer architectures are often over parameterized for the small, low-dimensional datasets typical of...
Echoverse: Deep, evolving environments for computer-use agents
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve.
The post Echoverse: Deep, evolving environ...
EvoLib: Turning experience into evolving knowledge
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment.
The post EvoLib: Turning experience into evolving knowledge appeared first on Microsoft Researc...
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.
ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science
arXiv:2607.26155v1 Announce Type: new
Abstract: Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories. We introduce CL...