Search Results for author:
Found 55 papers, 22 papers with code
Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms
Current virtual assistant (VA) platforms are beholden to the limited number of languages they support.
ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
ModelingBench also supports multiple valid solutions, capturing the ambiguity and creativity of practical modeling.
RM-R1: Reward Modeling as Reasoning
The training of RM-R1 consists of two key stages: (1) distillation of high-quality reasoning chains and (2) reinforcement learning with verifiable rewards.
OTC: Optimal Tool Calls via Reinforcement Learning
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools, such as search engines and code interpreters, to solve tasks beyond the capabilities of language-only reasoning.
ToolRL: Reward is All Tool Learning Needs
In this work, we present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm.
Alice: Proactive Learning with Teacher's Demonstrations for Weak-to-Strong Generalization
In this work, we introduce Alice (pro{A}ctive {l}earning w{i}th tea{c}her's D{e}monstrations), a framework that leverages complementary knowledge between teacher and student to enhance the learning process. We probe the knowledge base of the teacher model by eliciting their uncertainty, and then use these insights together with teachers' responses as demonstrations to guide student models in self-generating improved responses for supervision.
A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
Recent advances in Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users.
AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and \textbf{R}esponse Pairs.
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
To address it, we propose a novel concept: knowledge overshadowing, where model's dominant knowledge can obscure less prominent knowledge during text generation, causing the model to fabricate inaccurate details.
SMART: Self-Aware Agent for Tool Overuse Mitigation
To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary.
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks.
Internal Activation as the Polar Star for Steering Unsafe LLM Behavior
Large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks but also pose significant risks due to their potential to generate harmful content.
EscapeBench: Pushing Language Models to Think Outside the Box
Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments.
FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs
In this work, we propose FastAttention which pioneers the adaptation of FlashAttention series for NPUs and low-resource GPUs to boost LLM inference efficiency.
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
These experiments reveal that while most current models are robust against the "lost in the middle" issue, there exist significant biases related to the spacing of relevant information pieces.
Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents.
Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration
We present a refined approach to biomedical question-answering (QA) services by integrating large language models (LLMs) with Multi-BERT configurations.
Aligning LLMs with Individual Preferences via Interaction
To address this gap, we train LLMs that can ''interact to align'', essentially cultivating the meta-skill of LLMs to implicitly infer the unspoken personalized preferences of the current user through multi-turn conversations, and then dynamically align their following behaviors and responses to these inferred preferences.
HSF: Defending against Jailbreak Attacks with Hidden State Filtering
With the growing deployment of LLMs in daily applications like chatbots and content generation, efforts to ensure outputs align with human values and avoid harmful content have intensified.
Practical token pruning for foundation models in few-shot conversational virtual assistant systems
The VA system is expected to be a cost-efficient SaaS service with low training and inference time while achieving high accuracy even with a small number of training samples.
PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations
In this work, we introduce PianoMime, a framework for training a piano-playing agent using internet demonstrations.
Zero-Shot Generalization during Instruction Tuning: Insights from Similarity and Granularity
For the first time, we show that zero-shot generalization during instruction tuning is a form of similarity-based generalization between training and test data at the instance level.
Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning
Ultrasound (US) has been widely used in daily clinical practice for screening internal organs and guiding interventions.
LanePtrNet: Revisiting Lane Detection as Point Voting and Grouping on Curves
from object detection and segmentation tasks, while these approaches require manual adjustments for curved objects, involve exhaustive searches on predefined anchors, require complex post-processing steps, and may lack flexibility when applied to real-world scenarios. In this paper, we propose a novel approach, LanePtrNet, which treats lane detection as a process of point voting and grouping on ordered sets: Our method takes backbone features as input and predicts a curve-aware centerness, which represents each lane as a point and assigns the most probable center point to it.
Reconstruction-Based Anomaly Localization via Knowledge-Informed Self-Training
Most existing reconstruction-based methods only use normal samples to construct model.
Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution.
Triple Simplex Matrix Completion for Expense Forecasting
Forecasting project expenses is a crucial step for businesses to avoid budget overruns and project failures.
Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
We first validate the efficacy of Toolink in harnessing the model's creativity and CoS ability on ChatGPT.
"Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs
Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge.
The 2nd Place Solution for 2023 Waymo Open Sim Agents Challenge
In this technical report, we present the 2nd place solution of 2023 Waymo Open Sim Agents Challenge (WOSAC)[4].
Recyclable Tuning for Continual Pre-training
In pilot studies, we find that after continual pre-training, the upgraded PLM remains compatible with the outdated adapted weights to some extent.
DeCom: Deep Coupled-Factorization Machine for Post COVID-19 Respiratory Syncytial Virus Prediction with Nonpharmaceutical Interventions Awareness
Respiratory syncytial virus (RSV) is one of the most dangerous respiratory diseases for infants and young children.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
One-Bit Covariance Reconstruction with Non-zero Thresholds: Algorithm and Performance Analysis
To mitigate this issue, we present a recovery scheme that incorporates time-varying thresholds.
Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants
Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query.
Exploring Mode Connectivity for Pre-trained Language Models
(3) How does the PLM's task knowledge change along the path connecting two minima?
GOCPT: Generalized Online Canonical Polyadic Tensor Factorization and Completion
Our variant GOCPTE shows up to 1:2% and 5:5% fitness improvement on two datasets with about 20% speedup compared to the best model.
Clinical trial site matching with improved diversity using fair policy learning
More recently, the issue of diversity and inclusion in clinical trials is gaining importance.
JULIA: Joint Multi-linear and Nonlinear Identification for Tensor Completion
Tensor completion aims at imputing missing entries from a partially observed tensor.
ATD: Augmenting CP Tensor Decomposition by Self Supervision
This paper addresses the above challenges by proposing augmented tensor decomposition (ATD), which effectively incorporates data augmentations and self-supervised learning (SSL) to boost downstream classification.
MTC: Multiresolution Tensor Completion from Partial and Coarse Observations
Our MTC model explores tensor mode properties and leverages the hierarchy of resolutions to recursively initialize an optimization setup, and optimizes on the coupled system using alternating least squares.
Condition Integration Memory Network: An Interpretation of the Meaning of the Neuronal Design
When a neuron's activation represents some symbolic element in the environment, each of its synapses can indicate a potential change to the element and its future state.
Multi-version Tensor Completion for Time-delayed Spatio-temporal Data
Recovering such missing or noisy (under-reported) elements of the input tensor can be viewed as a generalized tensor completion problem.
One-Bit Target Detection in Collocated MIMO Radar and Performance Degradation Analysis
Target detection is an important problem in multiple-input multiple-output (MIMO) radar.
STELAR: Spatio-temporal Tensor Factorization with Latent Epidemiological Regularization
Accurate prediction of the transmission of epidemic diseases such as COVID-19 is crucial for implementing effective mitigation measures.
Learning Barrier Functions with Memory for Robust Safe Navigation
Control barrier functions are widely used to enforce safety properties in robot motion planning and control.
Motion Planning
Robotics
SWIFT: Scalable Wasserstein Factorization for Sparse Nonnegative Tensors
In particular, we define the N-th order tensor Wasserstein loss for the widely used tensor CP factorization and derive the optimization algorithm that minimizes it.
On the Compression of Translation Operator Tensors in FMM-FFT-Accelerated SIE Simulators via Tensor Decompositions
Tensor decomposition methodologies are proposed to reduce the memory requirement of translation operator tensors arising in the fast multipole method-fast Fourier transform (FMM-FFT)-accelerated surface integral equation (SIE) simulators.
Model-aided Deep Neural Network for Source Number Detection
Specifically, we first propose the eigenvalue based regression network (ERNet) and classification network (ECNet) to estimate the number of non-coherent sources, where the eigenvalues of the received signal covariance matrix and the source number are used as the input and the supervise label of the networks, respectively.
REP: Predicting the Time-Course of Drug Sensitivity
Time-course gene expression data is a rich source of information that can be used to unravel these complex processes, identify biomarkers of drug sensitivity and predict the response to a drug.
High-dimensional Gaussian graphical model for network-linked data
Graphical models are commonly used to represent conditional dependence relationships between variables.
From Gene Expression to Drug Response: A Collaborative Filtering Approach
Predicting the response of cancer cells to drugs is an important problem in pharmacogenomics.
