Zero-Run auditing supplies valid lower bounds on differential privacy parameters from fixed member and non-member datasets by modeling and correcting distribution-shift confounding via causal-inference techniques.
mega hub Canonical reference
LLaMA: Open and Efficient Foundation Language Models
Canonical reference. 82% of citing Pith papers cite this work as background.
1051
Pith papers citing it
Background
82% of classified citations
abstract
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.
hub tools
citation-role summary
background 206
method 19
baseline 8
other 6
dataset 1
extension 1
citation-polarity summary
claims ledger
- abstract We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
Fragmentation strictly raises optimal finite-context log-loss on Markov sources while tokenization can make a short token window equivalent to a longer source window under reliability and compression conditions.
Allowing each quantization group to select among multiple 4-bit grids improves accuracy over single-grid FP4 for both post-training and pre-training of LLMs.
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
An adversary controlling an intermediate pipeline stage in decentralized LLM post-training can inject a backdoor that reduces alignment from 80% to 6%, with the backdoor persisting in 60% of cases even after subsequent safety training.
First study of 1,899 MCP servers finds eight distinct vulnerabilities (only three traditional), 7.2% with general issues, 5.5% with tool poisoning, and 66% with code smells, urging MCP-specific security practices.
BEAVER is the first text-to-SQL benchmark from private enterprise data warehouses, revealing SOTA agentic frameworks achieve only 10.8% accuracy on complex real-world queries.
MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.
AgentClinic is a multimodal agent benchmark demonstrating that LLM diagnostic accuracy on MedQA drops to below one-tenth in sequential clinical simulations, with Claude-3.5 leading and large tool-use differences across models.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
BLaIR is a new benchmark and 570M-review dataset showing that LLM performance rankings on recommendation tasks have little correlation with rankings on general embedding benchmarks like MTEB.
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.
API-Bank is a new benchmark and training dataset for tool-augmented LLMs that shows fine-tuned models can approach GPT-3.5 tool-use effectiveness.
GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.
A new sensitivity-labeled test collection is released from Enron emails with crowdsourced queries, relevance judgments, and LLM extensions for evaluating sensitivity-aware search.
SPARE reformulates visual token pruning as column subset selection to minimize reconstruction error and uses anti-relevance for context-aware selection in VLMs.
Orli is an autoregressive image-to-sequence model that jointly detects text lines and determines their reading order on historical documents via chord-frame baselines, trained on 196k pages across ten scripts.
Defines cost-aware RAG with evidence cost tiers and shows static selectors are brittle while agentic LLM-based selection is promising but model-dependent.
RWGBench is a citation-centric benchmark for related work generation built from 40k CS papers and a 100-paper test set, with multi-dimensional metrics that better match human expert judgment than standard similarity scores.
Introduces nexbax, a diagnostic framework with three themes and 10 dimensions for evaluating AI economic viability, operational practicality, and societal integrity in next-billion-user contexts.
citing papers explorer
-
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
OmniCompliance-100K supplies 12,985 distinct rules and 106,009 associated real-world cases from 74 multi-domain regulations to benchmark LLM safety and compliance.
-
Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows
This work delivers the first measurements of performance-energy trade-offs across four multi-request LLM workflow patterns on A100 GPUs using vLLM and Parrot.
-
PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems
PrefixWall mitigates APC side channels in multi-tenant LLM systems via selective prefix isolation, delivering up to 70% higher cache reuse and 30% lower latency than full-isolation baselines.
-
Evaluating the Search Agent in a Parallel World
Mind-ParaWorld creates parallel worlds with atomic facts to evaluate search agents on future scenarios, showing they synthesize evidence well but struggle with collection, coverage, sufficiency judgment, and stopping decisions.
-
SCP: Spatial Causal Prediction in Video
SCP defines a new benchmark task for predicting spatial causal outcomes beyond direct observation and shows that 23 leading models lag far behind humans on it.
-
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
-
Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding
Mema adds a stateful memory module to vision encoders that accumulates hierarchical visual features across layers and selectively injects portions back via feedback to preserve fine-grained cues, yielding consistent gains on multimodal benchmarks.
-
SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses
SUPERGLASSES is the first VQA benchmark built from actual smart glasses data, and SUPERLENS is an agent using automatic object detection, query decoupling, and multimodal search that outperforms GPT-4o by 2.19% on it.
-
LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
LongVideo-R1 trains a reasoning agent on 33K trajectories to intelligently select informative video clips via iterative refinement and RL, achieving better accuracy-efficiency tradeoffs on long video QA benchmarks.
-
Integrating Domain-Specialized Language Models with AI Measurement Tools for Deterministic Atomic-Resolution Experimentation
Domain-specialized small language models enable deterministic atomic-resolution scanning probe microscopy control with 99.3% command accuracy, lower computational cost, and better domain performance than larger general models.
-
FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios
FedUTR fuses textual item representations with user interactions via fusion and adaptation modules to improve federated recommendations under high sparsity, with up to 59% gains over baselines and convergence guarantees.
-
SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips
SuperInfer improves TTFT SLO attainment by up to 74.7% on GH200 Superchips via SLO-aware rotary scheduling (RotaSched) and full-duplex KV cache rotation (DuplexKV) over NVLink-C2C while preserving TBT and throughput.
-
CompNO: A Novel Foundation Model approach for solving Partial Differential Equations
CompNO composes specialized Fourier neural operator blocks for fundamental differential operators into task-specific solvers that achieve lower L2 error than baselines on linear parametric PDEs and remain competitive on nonlinear flows while exactly satisfying boundaries.
-
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation
Disco-RAG improves RAG by building intra-chunk discourse trees and inter-chunk rhetorical graphs that feed into a planning blueprint, delivering state-of-the-art results on question answering and long-document summarization without any fine-tuning.
-
Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems
The paper delivers the first comprehensive review and unified taxonomy of agentic AI in remote sensing, covering single-agent copilots, multi-agent systems, planning mechanisms, benchmarks, and a roadmap while noting limitations in grounding and safety.
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
-
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
4D-RGPT uses perceptual 4D distillation to boost region-level 4D perception in multimodal LLMs and reports gains on existing and new video QA benchmarks.
-
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.
-
Large Video Planner Enables Generalizable Robot Control
A video foundation model trained on human demonstrations generates zero-shot plans that convert to executable robot actions on novel scenes and tasks.
-
Group Representational Position Encoding
GRAPE unifies RoPE and ALiBi as special cases of group actions on positions, providing a principled design space for positional encodings via SO(d) rotations and GL unipotent transformations.
-
Teaching Language Models Mechanistic Explainability Through MechSMILES
MechSMILES lets language models predict complete reaction mechanisms with 93% pathway retrieval on key benchmarks and adapt to new reaction classes from as few as 40 examples.
-
SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
SpatialBench creates a five-level framework and 15-task benchmark to measure hierarchical spatial reasoning in MLLMs, finding strong basic perception but weak symbolic reasoning, causal inference, and planning.
-
SoK: Honeypots & LLMs, More Than the Sum of Their Parts?
A systematization of knowledge paper that taxonomizes honeypot detection vectors, synthesizes LLM-honeypot literature into canonical architecture and evaluation methods, and proposes a roadmap for autonomous deception systems.
-
On Interaction Effects in Greybox Fuzzing
MuoFuzz improves greybox fuzzing by learning mutator sequence interactions to select effective orders, outperforming AFL++ and MOPT on coverage and unique bugs in FuzzBench and MAGMA.
-
When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
LAGA is a unified multi-agent LLM framework that automates comprehensive quality optimization for text-attributed graphs by running detection, planning, action, and evaluation agents in a closed loop.
-
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
Low-precision Flash Attention fails due to similar low-rank attention representations combined with biased rounding errors that accumulate and corrupt weight updates; a minimal fix to reduce rounding bias stabilizes training.
-
SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
SeedPrints fingerprints LLMs using persistent biases from initialization seeds for lineage verification across pretraining and adaptation stages.
-
LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
LogitTrace detects benchmark contamination by showing that contaminated inputs produce earlier stabilization in layerwise logit trajectories while clean inputs show more gradual accumulation.
-
FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new BG-Flicker metric.
-
PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs
PromptCOS is a content-only watermarking method for LLM system prompts that embeds detectable cyclic signals via auxiliary tokens while preserving fidelity and resisting removal attacks.
-
mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA
mKG-RAG constructs multimodal KGs via MLLM-driven extraction and vision-text matching then applies dual-stage query-aware retrieval to achieve new state-of-the-art results on knowledge-based VQA.
-
OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction
OKG-LLM constructs an Ocean Knowledge Graph, learns its embeddings, fuses them with SST observations, and applies an LLM to outperform prior methods on global sea surface temperature prediction.
-
Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
Deliberative Searcher integrates retrieval search, multi-step verification, and RL training with a soft reliability constraint to improve alignment between LLM confidence and correctness in open-domain QA.
-
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
-
Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Presents Reason50K dataset and ReasonBrain framework for hypothetical instruction-based image editing that requires physical, temporal, causal, and story reasoning.
-
PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
PuzzleWorld benchmark reveals state-of-the-art AI models solve only 18% of complex puzzlehunt problems with 40% stepwise accuracy, matching novices but trailing enthusiasts, while fine-tuning on traces yields modest gains.
-
Gen-n-Val: Agentic Image Data Generation and Validation
Gen-n-Val uses LLM and VLLM agents with Layer Diffusion and TextGrad to generate and validate synthetic instance data, cutting invalid samples from 50% to 7% and improving rare-class performance on LVIS and COCO benchmarks.
-
Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs
DORI benchmark shows top vision-language models reach only 54.2% accuracy on coarse orientation tasks and 33% on granular judgments, with sharp drops on reference-frame shifts and compound rotations.
-
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
CAD-Coder generates valid CadQuery scripts from text via supervised fine-tuning followed by reinforcement learning with geometric Chamfer Distance rewards and chain-of-thought planning.
-
FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry
FractalMamba++ scales Vision Mamba across resolutions by using Hilbert fractal serialization, hierarchy-based skip connections, and fractal-aware 2D rotary position encoding.
-
Transfer between Modalities with MetaQueries
MetaQueries act as an efficient bridge allowing multimodal LLMs to augment diffusion-based image generation and editing without complex training or unfreezing the LLM backbone.
-
Toward Generalizable Forgery Detection and Reasoning
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
-
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.
-
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.
-
LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
LLM-TabLogic extracts inter-column logical constraints using LLMs and conditions a score-based latent diffusion model on them to generate synthetic tabular data that preserves those relationships.
-
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation, delivering 9-18% accuracy gains and 11% latency reduction.
-
Sundial: A Family of Highly Capable Time Series Foundation Models
Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.
-
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
OCRBench v2 is a new benchmark with four times more tasks than prior versions that reveals most large multimodal models score below 50 out of 100 on visual text tasks and share five specific weaknesses.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
Federated Co-tuning Framework for Large and Small Language Models
FedCoLLM is a parameter-efficient federated co-tuning framework that improves client SLMs via server LLMs and enriches LLMs with client domain insights using adapters on NLP text generation tasks.