· ai
[Paper] Auditing Games for Sandbagging
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagg...
-
- · ai
[Paper] LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Readout
Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural network...
- · ai
[Paper] Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes
Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. Th...
- · ai
[Paper] Multi-view Pyramid Transformer: Look Coarser to See Broader
We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds...
- · ai
[Paper] Group Representational Position Encoding
We present GRAPE (Group RepresentAtional Position Encoding), a unified framework for positional encoding based on group actions. GRAPE brings together two famil...
- · ai
[Paper] OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrati...
- · ai
[Paper] Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support
LLM-based agents are rapidly being plugged into expert decision-support, yet in messy, high-stakes settings they rarely make the team smarter: human-AI teams of...
- · devops
[Paper] Quantifying the Carbon Reduction of DAG Workloads: A Job Shop Scheduling Perspective
Carbon-aware schedulers aim to reduce the operational carbon footprint of data centers by running flexible workloads during periods of low carbon intensity. Mos...
- · ai
[Paper] Large Causal Models from Large Language Models
We introduce a new paradigm for building large causal models (LCMs) that exploits the enormous potential latent in today's large language models (LLMs). We desc...
- · ai
[Paper] ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, ...
- · devops
[Paper] Designing Co-operation in Systems of Hierarchical, Multi-objective Schedulers for Stream Processing
Stream processing is a computing paradigm that supports real-time data processing for a wide variety of applications. At Meta, it's used across the company for ...
- · ai
[Paper] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training tr...