Decentralized learning (DL) enables a set of nodes to train a model collaboratively without central coordination, offering benefits for privacy and scalability....
This paper studies an important rate allocation problem that arises in many networked and distributed systems: steady-state traffic rate allocation from multipl...
Distributed Stream Processing Systems (DSPSs) form the backbone of real-time processing and analytics at ByteDance, where Apache Flink powers one of the largest...
Large language Model (LLM)-assisted algorithm discovery is an iterative, black-box optimization process over programs to approximatively solve a target task, wh...
Dynamic scheduling of task graphs is often addressed without revisiting prior task allocations, with a primary focus on minimizing makespan. We study controlled...
Advanced Persistent Threats (APTs) are sophisticated, long-term cyberattacks that are difficult to detect because they operate stealthily and often blend into n...
Detecting rare and diverse anomalies in highly imbalanced datasets-such as Advanced Persistent Threats (APTs) in cybersecurity-remains a fundamental challenge f...
Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve...
Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient gen...
Pixel diffusion generates images directly in pixel space in an end-to-end manner, avoiding the artifacts and bottlenecks introduced by VAEs in two-stage latent ...
We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, ampli...
LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternativ...
The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference ...
Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action...
Large language models (LLMs) have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning. Nevertheless, at the limits ...
AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs....
Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-...
Enabling humanoid robots to perform agile and adaptive interactive tasks has long been a core challenge in robotics. Current approaches are bottlenecked by eith...
Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expan...
Deep learning based auto segmentation is increasingly used in radiotherapy, but conventional models often produce anatomically implausible false positives, or h...
Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning suc...
Rapid advancements in large language models (LLMs) have sparked the question whether these models possess some form of consciousness. To tackle this challenge, ...
Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capabl...
Activation decomposition methods in language models are tightly coupled to geometric assumptions on how concepts are realized in activation space. Existing appr...
