World Value Models for Robotic Manipulation
Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value estimation demands deep temporal...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
Long-horizon LLM agents can fail quietly: they settle on one reading of the evidence early, then spend the rest of the run defending it. We call this premature commitment. Final-an...
Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
Procedural memory is increasingly used to improve LLM agents on recurring workplace tasks, yet its ability to produce reusable skills remains poorly understood. We introduce AFTER,...
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reli...
Critique of Agent Model
What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI co-scientists'', and other ``agentic" tools that ...
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems. The book covers the full stack from first principles to product...
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an ...
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive...
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However,...
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can ar...
TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM j...
Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
Reconstructing dynamic non-rigid objects from monocular video requires integrating visual cues from direct observations with data-driven priors over geometry and appearance. Prior ...
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data s...
Semantic Browsing: Controllable Diversity for Image Generation
Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a ...
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the quer...
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally r...
Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents
Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored. Detecting failures in long-horizon robotic tasks is par...
MeshFlow: Mesh Generation with Equivariant Flow Matching
Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permuta...
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard. Large retrieval benchmar...
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy or avoid. In authoring, this ...
ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments
We introduce ShotcreteDepth, a bi-modal dataset from the construction domain that captures both an active shotcreting process and general construction environments. The dataset com...
ChartWalker: Benchmarking the Cross-Chart RAG Task
Cross-Chart Retrieval-Augmented Generation (RAG) is critical for complex multi-modal analytical tasks in scientific, business, and political domains. However, existing benchmarks e...
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents
Long-horizon agents depend on context management: systems compress, summarize, and evict old tokens so tasks can continue beyond finite windows. That is safe only when dropped info...
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synt...