@@ -50,6 +50,21 @@ what-one-cannot-two-can:
5050 annotation : " (spotlight)"
5151 image : " ./images/what-one-cannot.png"
5252
53+ multimodal-fusion-balancing :
54+ title : " Multimodal Fusion Balancing Through Game-Theoretic Regularization"
55+ date : 2025-12
56+ authors :
57+ - Konstantinos Kontras
58+ - Thomas Strypsteen
59+ - Christos Chatzichristos
60+ - Paul Pu Liang
61+ - Matthew Blaschko
62+ - Maarten De Vos
63+ journal : " NeurIPS 2025"
64+ annotation : " (spotlight)"
65+ link : https://arxiv.org/pdf/2411.07335
66+ image : " ./images/fusiongame.png"
67+
5368mimeqa :
5469 title : " MimeQA: Towards socially-intelligent nonverbal foundation models"
5570 date : 2025-12
7388 - Paul Pu Liang
7489 journal : " NeurIPS 2025"
7590 link : https://arxiv.org/abs/2510.04417
76-
77- multimodal-fusion-balancing :
78- title : " Multimodal Fusion Balancing Through Game-Theoretic Regularization"
79- date : 2025-12
80- authors :
81- - Konstantinos Kontras
82- - Thomas Strypsteen
83- - Christos Chatzichristos
84- - Paul Pu Liang
85- - Matthew Blaschko
86- - Maarten De Vos
87- journal : " NeurIPS 2025"
88- annotation : " (spotlight)"
89- link : https://arxiv.org/pdf/2411.07335
91+ image : " ./images/thinpid.png"
9092
9193position-simulating-society :
9294 title : " Position: Simulating Society Requires Simulating Thought"
@@ -107,6 +109,7 @@ position-simulating-society:
107109 - Kent Larson
108110 journal : " NeurIPS 2025"
109111 link : https://arxiv.org/pdf/2506.06958
112+ image : " ./images/simulatesociety.png"
110113
111114fairgrpo :
112115 title : " FairGRPO: Towards Fair Reasoning Foundation Models for Clinical Diagnosis"
@@ -118,6 +121,7 @@ fairgrpo:
118121 - Paul Pu Liang
119122 journal : " arXiv preprint"
120123 link : https://openreview.net/pdf?id=D0SgzgdBjo
124+ image : " ./images/fairgrpo.png"
121125
122126page-4d :
123127 title : " Page-4D: Disentangled Pose and Geometry Estimation for 4D Perception"
@@ -133,6 +137,7 @@ page-4d:
133137 - Mengyu Wang
134138 journal : " arXiv preprint"
135139 link : https://arxiv.org/pdf/2510.17568
140+ image : " ./images/page4d.gif"
136141
137142human-behavior-atlas :
138143 title : " Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding"
@@ -151,6 +156,7 @@ human-behavior-atlas:
151156 - Paul Pu Liang
152157 journal : " arXiv preprint"
153158 link : https://arxiv.org/pdf/2510.04899
159+ image : " ./images/hba.png"
154160
155161dialogues-with-ai :
156162 title : " Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skills"
@@ -163,6 +169,7 @@ dialogues-with-ai:
163169 - Pattie Maes
164170 journal : " arXiv preprint"
165171 link : https://arxiv.org/pdf/2510.01537
172+ image : " ./images/dialog.png"
166173
167174radar :
168175 title : " RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis"
@@ -175,6 +182,7 @@ radar:
175182 - Paul Pu Liang
176183 journal : " arXiv preprint"
177184 link : https://arxiv.org/pdf/2508.16850
185+ image : " ./images/radar.png"
178186
179187learn-globally-speak-locally :
180188 title : " Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning"
@@ -190,6 +198,7 @@ learn-globally-speak-locally:
190198 - Paul Pu Liang
191199 journal : " arXiv preprint"
192200 link : https://arxiv.org/pdf/2507.05418
201+ image : " ./images/multilingualreasoning.png"
193202
194203climb :
195204 title : " CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models"
@@ -293,6 +302,7 @@ fits-like-a-flex-glove:
293302 - Wojciech Matusik
294303 journal : " CHI 2025 Late-Breaking Work"
295304 link : https://arxiv.org/pdf/2503.06349
305+ image : " ./images/glove.png"
296306
297307compositionality :
298308 title : " Progressive Compositionality In Text-to-Image Generative Models"
@@ -305,6 +315,7 @@ compositionality:
305315 journal : " ICLR 2025"
306316 annotation : " (spotlight)"
307317 link : https://arxiv.org/abs/2410.16719
318+ image : " ./images/evogen.gif"
308319
309320osatlas :
310321 title : " OS-ATLAS: A Foundation Action Model for Generalist GUI Agents"
@@ -324,6 +335,7 @@ osatlas:
324335 journal : " ICLR 2025"
325336 annotation : " (spotlight)"
326337 link : https://arxiv.org/abs/2410.23218
338+ image : " ./images/osatlas.png"
327339
328340videowebarena :
329341 title : " VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks"
@@ -339,6 +351,7 @@ videowebarena:
339351 - Kazuhito Koishida
340352 journal : " ICLR 2025"
341353 link : https://arxiv.org/abs/2410.19100
354+ image : " ./images/videowebarena.png"
342355
343356teasergen :
344357 title : " TeaserGen: Generating Teasers for Long Documentaries"
@@ -352,6 +365,7 @@ teasergen:
352365 - Hao-Wen Dong
353366 journal : " ICLR 2025"
354367 link : https://arxiv.org/abs/2410.05586
368+ image : " ./images/teasergen.png"
355369
356370bigbench :
357371 title : " Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models"
@@ -361,3 +375,4 @@ bigbench:
361375 journal : " ICLR 2025, TMLR 2023"
362376 annotation : " (finalist for outstanding certification)"
363377 link : https://openreview.net/forum?id=uyTL5Bvosj
378+ image : " ./images/bigbench.png"
0 commit comments