Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance taaft A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as… 2026-08-12 published
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project taaft Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) co… 2026-03-22 published
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases taaft Autoformalization translates informal natural language into formal, machine-verifiable languages. W… 2026-07-14 published
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling taaft Mobile devices continuously interact with cellular base stations, generating massive volumes of sig… 2026-03-27 published
Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty taaft Automated novelty judgment can accelerate scientific discovery by enabling efficient evaluation, re… 2026-08-26 published
Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks taaft Visual reasoning tasks require a system to jointly perceive visual content and apply formal relatio… 2026-09-04 published
Thinking effort aligns between humans and reasoning models in abductive reasoning taaft A major question in cognitive modeling concerns the behavioral alignment between large language mod… 2026-09-01 published
Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation taaft Recent advancements in unified generative models (UGMs) and world simulators have achieved unpreced… 2026-09-02 published
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model taaft Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecastin… 2026-03-23 published
Thread-Efficient Decoding for Neural Texture Compression taaft Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers fr… 2026-08-28 published
Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL taaft While self-supervised approaches to reinforcement learning have achieved strong results by learning… 2026-08-31 published
Through the Looking-Glass: AI-Mediated Video Communication Reduces Interpersonal Trust and Confidence in Judgments taaft AI-based tools that mediate, enhance or generate parts of video communication may interfere with ho… 2026-03-19 published
TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors taaft Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to har… 2026-09-04 published
TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Driven Optimization taaft Human trajectory forecasting is important for intelligent multimedia systems operating in visually… 2026-03-26 published
Tight Majorizations and Convergence Rates of Nuclear Norm Minimization IRLS taaft Iteratively reweighted least squares (IRLS) methods constitute a natural approach to nuclear norm m… 2026-08-24 published
Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription taaft In recent years, research on music transcription has focused mainly on architecture design and inst… 2023-09-27 published
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models taaft Time series forecasting holds significant importance in many real-world dynamic systems and has bee… 2023-10-03 published
Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation taaft Repurchase recommenders in e-commerce are commonly framed as a binary question asking "will this cu… 2026-08-28 published
TinyBERT: Distilling BERT for Natural Language Understanding taaft Language model pre-training, such as BERT, has significantly improved the performances of many natu… 2019-09-23 published
TinyLlama: An Open-Source Small Language Model taaft We present TinyLlama, a compact 1.1B language model pretrained on around 1 trillion tokens for appr… 2024-01-04 published
Tlow: Flow-based Item Tokenizer for Recommendation taaft Item tokenizer encodes semantic embeddings into token IDs to replace the randomly assigned item IDs… 2026-08-25 published
To What Extent Do Large Language Models Understand Bangla Idioms? taaft Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and pos… 2026-09-03 published
To Write or to Automate Linguistic Prompts, That Is the Question taaft LLM performance is highly sensitive to prompt design, yet whether automatic prompt optimization can… 2026-03-26 published
Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting taaft Black-box model attribution is increasingly relevant when large language models (LLMs) are served t… 2026-08-30 published
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data taaft Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, ear… 2026-08-31 published
Token-Level Advertising taaft Generative AI is transforming how people access information, challenging traditional advertising me… 2026-08-27 published
TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation taaft While data-driven 3D shape correspondence estimation has recently seen substantial progress, robust… 2026-09-03 published
TokTier: Exact Stateful Tokenization for Agentic LLM Serving taaft LLM serving caches prompt KV state, yet most front ends still re-tokenize the full request on every… 2026-07-31 published
Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator taaft Neural ocean emulators are being proposed for regional forecasting in cyclone-exposed coastal seas,… 2026-09-04 published
Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents taaft Augmenting large language models (LLMs) with external tools has emerged as a promising approach to… 2024-05-26 published
Toolformer: Language Models Can Teach Themselves to Use Tools Meta Platforms Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or t… 2023-02-09 published
ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Construction taaft Scientific benchmarks are commonly built by domain experts who write tasks and cross-check one anot… 2026-09-02 published
TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving taaft Prefix caching introduces a fundamental tradeoff in multi-agent large language model (LLM) serving:… 2026-08-26 published
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information taaft Existing GNN quantization methods suffer from considerable quantization overhead, which severely li… 2026-08-31 published
ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models taaft Pairwise preference labels rank complete images, yet Diffusion-DPO applies their effect over many s… 2026-09-03 published
Topological Steering taaft With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has be… 2026-09-01 published